Archive

Archive.py

#!/usr/bin/env python

import requests
import time
import os

with open("urls", "r") as f_urls, open("titles", "r") as f_titles:
    urls = f_urls.read().splitlines()
    titles = f_titles.read().splitlines()

if len(urls) != len(titles):
    print("Error: The number of urls and titles do not match.")
    exit(1)


def download_file(url, filename):
    response = requests.get(url, stream=True)
    if response.status_code == 200:
        with open(filename, "wb") as f:
            for chunk in response.iter_content(1024):
                f.write(chunk)
        print(f"Downloaded: {filename}")
        time.sleep(3)
    else:
        print(f"Failed to download ({response.status_code}): {url}")


for url, title in zip(urls, titles):
    epoch = os.path.basename(url).split(".")[0]
    filename = f"{epoch} {title}"
    download_file(url, filename)

Extract_links.js

const filenames = [];
const fileElements = document.getElementsByClassName("post_file_filename");
for (let i = 0; i < fileElements.length; i++) {
  const title = fileElements[i].getAttribute("title");
  filenames.push(title ? title : fileElements[i].textContent);
}

const imagelinks = [];
const linkElements = document.getElementsByClassName("thread_image_link");
for (let i = 0; i < linkElements.length; i++) {
  imagelinks.push(linkElements[i].href);
}

function download(filename, text) {
  const blob = new Blob([text], { type: "text/plain" });
  const url = URL.createObjectURL(blob);
  const a = document.createElement("a");
  a.href = url;
  a.download = filename;
  a.click();
  URL.revokeObjectURL(url);
}

download("titles", filenames.join("\n"));
download("urls", imagelinks.join("\n"));