Last active
April 4, 2020 14:29
-
-
Save divadsn/e1e7691b0bc6bb88a0d3680912bb0842 to your computer and use it in GitHub Desktop.
Proof of concept extractor script for cda.pl video links, reverse engineered from updated player.js
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
import json | |
import urllib.request | |
from urllib.parse import unquote | |
from bs4 import BeautifulSoup | |
def decrypt(a: str): | |
a = unquote(a.replace("_XDDD", "")) | |
b = [] | |
for e in range(len(a)): | |
f = ord(a[e]) | |
b.append(chr(33 + (f + 14) % 94) if 33 <= f and 126 >= f else chr(f)) | |
a = "".join(b) | |
a = a.replace(".cda.mp4", "") | |
a = a.replace(".2cda.pl", ".cda.pl") | |
a = a.replace(".3cda.pl", ".cda.pl") | |
return a | |
if __name__ == '__main__': | |
url = "https://www.cda.pl/video/416037128" | |
# Trying to avoid as much trouble as possbile by "mocking" a real browser request | |
request = urllib.request.Request(url, headers={ | |
"Referer": "http://www.cda.pl", | |
"User-Agent": "Mozilla/5.0 (X11; Linux x86_64; rv:73.0) Gecko/20100101 Firefox/73.0" | |
}) | |
with urllib.request.urlopen(request) as response: | |
bs4 = BeautifulSoup(response, "html.parser") | |
tags = bs4.findAll("div") | |
for tag in tags: | |
if tag.has_attr("player_data"): | |
player_data = json.loads(tag["player_data"]) | |
break | |
file = player_data["video"]["file"] | |
print("https://" + decrypt(file) + ".mp4") |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Check the demo here: https://cda.codebucket.de/
Please note that currently some CDNs are working very slow, I am working on a workaround in the meantime.