
* fixed script (changed token entry from 'token' to 'jwt') * added subtitles * removed bunch of unused files * idk misc fixes prob check diff
320 lines
12 KiB
Python
320 lines
12 KiB
Python
# Pre-requisites:
|
|
# * N_m3u8DL-RE and mp4decrypt in current directory
|
|
# * ffmpeg in PATH
|
|
# * pip install -r requirements.txt
|
|
|
|
|
|
import argparse
|
|
import requests
|
|
import subprocess
|
|
import os
|
|
from bs4 import BeautifulSoup
|
|
import json
|
|
import platform # check for windows OS
|
|
import shutil # check for ffmpeg in PATH
|
|
import browser_cookie3 # cookies for premium accs
|
|
from fake_useragent import UserAgent # sets useragent
|
|
import concurrent.futures # concurrent downloads when using a -file
|
|
from cdm.wks import WvDecrypt, device_android_generic, PsshExtractor, KeyExtractor
|
|
|
|
# dont need any of these headers but makes it look like normal clients at least
|
|
# for extra "normal behavior": save the UA chosen here in some temp file so we can use the same one every time this utility is run
|
|
headers = {
|
|
'User-Agent': UserAgent(platforms='pc', min_version=122.0).random,
|
|
'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,image/avif,image/webp,*/*;q=0.8',
|
|
'Accept-Language': 'en-US,en;q=0.5',
|
|
'Cache-Control': 'no-cache',
|
|
}
|
|
|
|
if platform.system() == "Windows":
|
|
windows_flag = True
|
|
else:
|
|
windows_flag = False
|
|
|
|
|
|
parser = argparse.ArgumentParser(description='PYWKS-NPO')
|
|
parser.add_argument('-url', dest='url', required=False, help='NPO Video URL')
|
|
parser.add_argument('-file', dest='file', required=False, help='File with NPO Video URLs, one per line')
|
|
args = parser.parse_args()
|
|
|
|
|
|
def parse_url_file(file_path):
|
|
with open(file_path, 'r') as file:
|
|
urls = [line.strip() for line in file]
|
|
return urls
|
|
|
|
if args.file and args.url:
|
|
print("ERR: Please specify just one argument.")
|
|
print("-url: input NPO video URL")
|
|
print("-file: input a file with NPO video URLS, one per line")
|
|
exit()
|
|
elif args.file:
|
|
urls = parse_url_file(args.file)
|
|
elif args.url:
|
|
urls = [args.url]
|
|
else:
|
|
print("ERR: Please input your URL(s).")
|
|
print("-url: input NPO video URL")
|
|
print("-file: input a file with NPO video URLS, one per line")
|
|
exit()
|
|
|
|
|
|
def find_cookies():
|
|
print("NPO Plus subscribers are able to download in 1080p instead of 540p.")
|
|
print("Are you an NPO Plus subscriber and logged in on your browser? (y/N)")
|
|
userinput = input().lower()
|
|
print("\033[F\033[K\033[F\033[K\033[F\033[K")
|
|
if not userinput or userinput.lower() != 'y':
|
|
return
|
|
|
|
# browser_cookie3.load() should use ALL browsers' cookies. If this doesn't work, replace browser_cookie3.load with browser_cookie3.<browser>.
|
|
# See notes at the end of this script for possible options. Example: browser_cookie3.chrome or browser_cookie3.librewolf.
|
|
cookies = browser_cookie3.librewolf(domain_name='npo.nl')
|
|
return cookies
|
|
|
|
|
|
def find_targetId(url):
|
|
# Get full HTML and extract productId and episode number
|
|
# "future proof" :)
|
|
response_targetId = requests.get(url)
|
|
content = response_targetId.content
|
|
|
|
try:
|
|
url_split = url.split("/")
|
|
target_slug = url_split[7]
|
|
except:
|
|
print("URL invalid.")
|
|
print("URL format: https://npo.nl/start/serie/wie-is-de-mol/seizoen-24/wie-is-de-mol_56/afspelen")
|
|
print(f"Your URL: {url}")
|
|
exit()
|
|
|
|
soup = BeautifulSoup(content, 'html.parser')
|
|
script_tag = soup.find('script', {'id': '__NEXT_DATA__'})
|
|
|
|
if script_tag:
|
|
script_content = script_tag.contents[0]
|
|
else:
|
|
print("Script tag not found.")
|
|
|
|
def search(data, target_slug):
|
|
if isinstance(data, list):
|
|
for item in data:
|
|
result = search(item, target_slug)
|
|
if result:
|
|
return result
|
|
elif isinstance(data, dict):
|
|
for key, value in data.items():
|
|
if key == "slug" and value == target_slug:
|
|
return data.get("productId"), data.get("programKey")
|
|
else:
|
|
result = search(value, target_slug)
|
|
if result:
|
|
return result
|
|
return None
|
|
|
|
data_dict = json.loads(script_content)
|
|
target_product_id = search(data_dict, target_slug)
|
|
return target_product_id
|
|
|
|
|
|
def find_CSRF(targetId, plus_cookie):
|
|
response_CSRF = requests.get('https://npo.nl/start/api/auth/session', headers=headers, cookies=plus_cookie)
|
|
response_cookies = response_CSRF.cookies.get_dict()
|
|
|
|
json_productId = {
|
|
'productId': targetId,
|
|
}
|
|
|
|
url = f'https://npo.nl/start/api/domain/player-token'
|
|
response_token = requests.get(url, cookies=response_cookies, headers=headers, params=json_productId)
|
|
token = response_token.json()["jwt"]
|
|
return token
|
|
|
|
|
|
|
|
def find_MPD(token, url, plus_cookie):
|
|
headers['Authorization'] = token
|
|
|
|
json_auth = {
|
|
'profileName': 'dash',
|
|
'drmType': 'widevine',
|
|
'referrerUrl': url,
|
|
}
|
|
response = requests.post('https://prod.npoplayer.nl/stream-link', headers=headers, json=json_auth, cookies=plus_cookie)
|
|
response_data = response.json()
|
|
stream_data = response_data.get('stream', {})
|
|
|
|
if stream_data.get('streamURL'):
|
|
return stream_data
|
|
else:
|
|
print("NO MPD URL - BAD TOKEN")
|
|
print(response_data)
|
|
exit()
|
|
|
|
|
|
def find_PSSH(mpd):
|
|
mpd_url = mpd.get('streamURL')
|
|
|
|
response = requests.get(mpd_url, headers=headers)
|
|
pssh_extractor = PsshExtractor(response.text)
|
|
pssh_value = pssh_extractor.extract_pssh()
|
|
return pssh_value, mpd_url
|
|
|
|
|
|
def find_key(mpd, pssh):
|
|
headers_license = {
|
|
'x-custom-data': mpd.get('drmToken'),
|
|
'origin': 'https://start-player.npo.nl',
|
|
'referer': 'https://start-player.npo.nl/',
|
|
}
|
|
|
|
cert_b64 = None
|
|
key_extractor = KeyExtractor(pssh, cert_b64, "https://npo-drm-gateway.samgcloud.nepworldwide.nl/authentication", headers_license)
|
|
keys = key_extractor.get_keys()
|
|
wvdecrypt = WvDecrypt(init_data_b64=pssh, cert_data_b64=cert_b64, device=device_android_generic)
|
|
raw_challenge = wvdecrypt.get_challenge()
|
|
data = raw_challenge
|
|
for key in keys:
|
|
if isinstance(key, list):
|
|
if key:
|
|
for key_str in key:
|
|
return key_str
|
|
|
|
|
|
def check_prereq():
|
|
if windows_flag == True:
|
|
prereq_filelist = ['mp4decrypt.exe', 'N_m3u8DL-RE.exe']
|
|
else:
|
|
prereq_filelist = ['mp4decrypt', 'N_m3u8DL-RE']
|
|
|
|
for file in prereq_filelist:
|
|
if not os.path.isfile(file):
|
|
print(f"ERR: {file} not found!")
|
|
print("Please check your directory and try again.")
|
|
exit()
|
|
if shutil.which("ffmpeg") is None:
|
|
print("ffmpeg not found in PATH.")
|
|
exit()
|
|
|
|
|
|
def create_filename(url, programKey):
|
|
# season title
|
|
# 1 2 3 4 5 6 7 8 (optional)
|
|
# create filename based on input URL: https://npo.nl/start/serie /wie-is-de-mol /seizoen-24 /wie-is-de-mol_56 /afspelen
|
|
# https://npo.nl/start/serie /de-avondshow-met-arjen-lubach /seizoen-8_1 /de-avondshow-met-arjen-lubach_93 /afspelen
|
|
# https://npo.nl/start/serie /taarten-van-abel /seizoen-17 /joto /afspelen
|
|
url_split = url.split("/")
|
|
title = url_split[7].split("_")[0]
|
|
season = url_split[6].split("_")[0]
|
|
filename_enc = title + "_" + season + "_ep-" + programKey + "_encrypted"
|
|
filename = filename_enc.replace("_encrypted", "")
|
|
return filename_enc, filename
|
|
|
|
def download(mpd_url, filename_enc, productId, filename):
|
|
# output: filename.m4a (audio), filename.mp4 (video), filename.vtt (subtitles)
|
|
|
|
subtitle_url = f'https://cdn.npoplayer.nl/subtitles/nl/{productId}.vtt'
|
|
response = requests.get(subtitle_url)
|
|
with open(f"{filename}.vtt", 'wb') as subtitle_file:
|
|
subtitle_file.write(response.content)
|
|
if windows_flag == True:
|
|
subprocess.run(['N_m3u8DL-RE.exe', '--auto-select', '--no-log', '--save-name', filename_enc, mpd_url], stdout=subprocess.DEVNULL)
|
|
else:
|
|
subprocess.run(['N_m3u8DL-RE', '--auto-select', '--no-log', '--save-name', filename_enc, mpd_url], stdout=subprocess.DEVNULL)
|
|
|
|
|
|
def decrypt(key, filename_enc, filename):
|
|
if windows_flag == True:
|
|
subprocess.run(['mp4decrypt.exe', '--key', key, str(filename_enc + ".mp4"), str(filename + "_video.mp4")], stdout=subprocess.DEVNULL)
|
|
subprocess.run(['mp4decrypt.exe', '--key', key, str(filename_enc + ".m4a"), str(filename + "_audio.m4a")], stdout=subprocess.DEVNULL)
|
|
else:
|
|
subprocess.run(['mp4decrypt', '--key', key, str(filename_enc + ".mp4"), str(filename + "_video.mp4")], stdout=subprocess.DEVNULL)
|
|
subprocess.run(['mp4decrypt', '--key', key, str(filename_enc + ".m4a"), str(filename + "_audio.m4a")], stdout=subprocess.DEVNULL)
|
|
|
|
|
|
def merge(filename):
|
|
ffmpeg_command = [
|
|
'ffmpeg', '-v', 'quiet', # '-v stats',
|
|
'-i', filename + "_video.mp4",
|
|
'-i', filename + "_audio.m4a",
|
|
'-i', filename + ".vtt", # Subtitle file
|
|
'-c:v', 'copy', # Copy video codec
|
|
'-c:a', 'copy', # Copy audio codec
|
|
'-c:s', 'mov_text', # Subtitle codec for MP4
|
|
'-map', '0:v:0', # Map video stream
|
|
'-map', '1:a:0', # Map audio stream
|
|
'-map', '2:s:0', # Map subtitle stream
|
|
'-strict', 'experimental',
|
|
filename + ".mp4"
|
|
]
|
|
|
|
subprocess.run(ffmpeg_command)
|
|
|
|
|
|
def clean(filename_enc, filename):
|
|
os.remove(filename_enc + ".mp4")
|
|
os.remove(filename_enc + ".m4a")
|
|
os.remove(filename + "_audio.m4a")
|
|
os.remove(filename + "_video.mp4")
|
|
os.remove(filename + ".vtt")
|
|
|
|
|
|
def check_file(filename):
|
|
if not os.path.exists(filename + ".mp4"):
|
|
print("File not found. Continue anyway? (y/N)")
|
|
userinput = input().lower()
|
|
if not userinput or userinput != 'y':
|
|
exit()
|
|
|
|
|
|
def execute(url, plus_cookie, process_no):
|
|
productId, programKey = find_targetId(url)
|
|
token = find_CSRF(productId,plus_cookie)
|
|
mpd = find_MPD(token, url, plus_cookie)
|
|
pssh, mpd_url = find_PSSH(mpd)
|
|
key = find_key(mpd, pssh)
|
|
check_prereq()
|
|
filename_enc, filename = create_filename(url, programKey)
|
|
download(mpd_url, filename_enc, productId, filename)
|
|
decrypt(key, filename_enc, filename)
|
|
merge(filename)
|
|
clean(filename_enc, filename)
|
|
check_file(filename)
|
|
return process_no # keeps track of process index to return x/y videos completed message
|
|
|
|
|
|
|
|
plus_cookie = find_cookies()
|
|
max_workers = min(os.cpu_count(), len(urls))
|
|
|
|
with concurrent.futures.ThreadPoolExecutor(max_workers=max_workers) as executor:
|
|
futures = [executor.submit(execute, url, plus_cookie, i + 1) for i, url in enumerate(urls)]
|
|
|
|
completed_videos = 0
|
|
print(f"0/{len(urls)} videos completed")
|
|
for future in concurrent.futures.as_completed(futures):
|
|
result = future.result()
|
|
completed_videos += 1
|
|
print("\033[F\033[K\033[F\033[K")
|
|
print(f"{completed_videos}/{len(urls)} video{'s'[:len(urls) != 1]} completed")
|
|
|
|
|
|
#########
|
|
# NOTES #
|
|
#########
|
|
# The downloader *should* work across every platform, linux/mac/win.
|
|
# It has not been extensively tested on anything but windows. DM me if you need help :D
|
|
# Discord: quinten._. (That includes the ._.)
|
|
|
|
# Supported browsers for NPO Plus cookies:
|
|
# (https://github.com/borisbabic/browser_cookie3#testing-dates--ddmmyy)
|
|
# * Chrome
|
|
# * Firefox
|
|
# * LibreWolf
|
|
# * Opera
|
|
# * Opera GX
|
|
# * Edge
|
|
# * Chromium
|
|
# * Brave
|
|
# * Vivaldi
|
|
# * Safari |