Download all PDF files from abandonware-magazines.org that have no album

abandonware_scrapper.py

import requests
from bs4 import BeautifulSoup
import os
import time
import zipfile
from urllib.parse import urljoin, urlparse
import urllib.request
import sys

BASE_URL = "https://www.abandonware-magazines.org/affiche_mag.php?mag={}&page={}"
DOWNLOAD_PAGE_BASE = "https://www.abandonware-magazines.org/"
DOWNLOAD_FOLDER = "downloads"
os.makedirs(DOWNLOAD_FOLDER, exist_ok=True)

def get_html(url):
	response = requests.get(url)
	response.raise_for_status()
	return response.text

def find_download_links(page_html):
	soup = BeautifulSoup(page_html, "html.parser")
	results = []
	# Find all <a> tags with "download.php" in href
	for a_tag in soup.find_all("a", href=lambda href: href and "download.php" in href):
		tr = a_tag.find_parent("tr")
		if not tr:
			continue
		next_tr = tr.find_next_sibling("tr")
		if not next_tr:
			continue
		# Look for image with "images/album_off.png" in src
		img = next_tr.find("img", src=lambda src: src and "images/album_off.png" in src)
		if img:
			results.append(urljoin(DOWNLOAD_PAGE_BASE, a_tag['href']))
	return results

def get_final_download_url(download_php_url):
	html = get_html(download_php_url)
	soup = BeautifulSoup(html, "html.parser")
	# Find <a> to download.abandonware.org
	for a_tag in soup.find_all("a", href=lambda href: href and "download.abandonware.org" in href):
		return a_tag['href'].strip()
	return None

def download_file(file_url, folder):
	print(f"Downloading '{file_url}'")
	local_filename = os.path.join(folder, os.path.basename(urlparse(file_url).path))
	urllib.request.urlretrieve(file_url, local_filename)
		
	with zipfile.ZipFile(local_filename,"r") as zip_ref:
		zip_ref.extractall(folder)	
	print(f"Downloaded: {local_filename}")
	
	os.remove(local_filename)

def main():
	if len(sys.argv) != 4:
			print("Usage: python abandonware_scrapper.py <magazine_id> <pagefrom> <pageto>")
			sys.exit(1)

	magazine_id = int(sys.argv[1])
	pagefrom = int(sys.argv[2])
	pageto = int(sys.argv[3])
		
	for page in range(pagefrom, pageto):
		print(f"Processing page {page}")
		url = BASE_URL.format(magazine_id, page)
		html = get_html(url)
		download_php_links = find_download_links(html)
		for link in download_php_links:
			final_url = get_final_download_url(link)
			if final_url:
				try:					
					download_file(final_url, DOWNLOAD_FOLDER)
					time.sleep(1)  # Be nice to the server
				except Exception as e:
					print(f"Failed to download {final_url}: {e}")
			else:
				print("No abandonware.org download link found on page.")

if __name__ == "__main__":
	main()