FSL Course PDF Downloader

download.py

#!/usr/bin/env python3
import sys
import requests
from requests.adapters import HTTPAdapter
from urllib3.util.retry import Retry
from concurrent.futures import ThreadPoolExecutor, as_completed
import time
import json
from tqdm import tqdm
import base64
from pathlib import Path
from pdfmerge import pdfmerge
from pypdf import PdfReader, PdfWriter

def decode_base64_json( encoded_str ):
	try:
		utf8_bytes = base64.b64decode(encoded_str)
		json_str = utf8_bytes.decode('utf-8')
		return json.loads(json_str)
	except Exception as e:
		print("Decode error:", e)
		return None

def create_session():
	session = requests.Session()
	retries = Retry(
		total=5,
		backoff_factor=1,
		status_forcelist=[429, 500, 502, 503, 504],
		allowed_methods=["GET"],
		raise_on_status=False
	)
	adapter = HTTPAdapter(max_retries=retries)
	session.mount("http://", adapter)
	session.mount("https://", adapter)
	return session

def download_file(url, save_path, session, try_stream=False):
	try:
		if not try_stream:
			# Quick, simple full-body request
			r = session.get(url, timeout=30)
			r.raise_for_status()
			save_path.write_bytes(r.content)
			print(f"✅ Downloaded (no stream): {save_path.name}")
			return
		else:
			# Streamed download (for big files / progress)
			with session.get(url, stream=True, timeout=30) as r:
				r.raise_for_status()
				total_size = int(r.headers.get('content-length', 0))
				block_size = 1024
				t = tqdm(total=total_size, unit='iB', unit_scale=True, desc=save_path.name)
				with open(save_path, 'wb') as f:
					for data in r.iter_content(block_size):
						t.update(len(data))
						f.write(data)
				t.close()
				if total_size != 0 and t.n != total_size:
					print(f"❌ Incomplete download: {url}")
	except Exception as e:
		if try_stream:
			print(f"⚠️ Stream failed, retrying without stream: {url} ({e})")
			download_file(url, save_path, session, try_stream=False)
		else:
			print(f"❌ Final failure: {url} ({e})")

def download_all( urls , output_dir="downloads" , max_workers=5 ):
	session = create_session()
	Path(output_dir).mkdir(parents=True, exist_ok=True)
	results = {}

	with ThreadPoolExecutor(max_workers=max_workers) as executor:
		future_to_url = {}
		for url in urls:
			filename = url.split("/")[-1]
			save_path = Path(output_dir) / filename
			if save_path.exists():
				print(f"✅ Already exists: {save_path.name}")
				results[url] = True
				continue
			future = executor.submit(download_file, url, save_path, session)
			future_to_url[ future ] = url

		for future in tqdm( as_completed( future_to_url ) , total=len( urls ) , desc="Downloading all" ):
			url = future_to_url[ future ]
			try:
				future.result()
				results[url] = True
			except Exception as e:
				print( f"⚠️ {url} failed: {e}" )
				results[ url ] = False

	return results

def merge_pdfs( pdf_paths , output_path ):
	writer = PdfWriter()
	page_offset = 0

	for pdf_path in pdf_paths:
		path = Path( pdf_path )
		reader = PdfReader( str( path ) )
		num_pages = len( reader.pages )

		# Append all pages
		writer.append( reader )

		# Add top-level bookmark pointing to first page of this PDF
		writer.add_outline_item(
			title=path.stem ,
			page_number=page_offset
		)

		print( f"✅ Added {path.name} ({num_pages} pages) at page offset {page_offset}" )
		page_offset += num_pages

	with open( output_path, "wb" ) as out_f:
		writer.write( out_f )

	print( f"\n🎉 Merged PDF with bookmarks saved to: {output_path}" )


if __name__ == "__main__":
	urls = decode_base64_json( sys.argv[ 1 ] )
	download_all( urls )
	save_paths = [ str( Path("downloads") / url.split("/")[-1] ) for url in urls ]
	# pdfmerge( save_paths , "merged_output.pdf" )
	merge_pdfs( save_paths , "merged_output.pdf" )

dropper.js

( ()=> {
	// target = https://open.win.ox.ac.uk/pages/fslcourse/website/online_materials.html
	// example = https://open.win.ox.ac.uk/pages/fslcourse/lectures/Reg_P1E1.pdf

	// <a class="card-link" href="../lectures/Struc_P1E4.pdf" target="_blank" style="font-family: Arial;">PDF slides</a>

	function base64_encode( js_obj ) {
		const seen = new WeakSet();
		const safe_string = JSON.stringify( js_obj , ( key , value ) => {
		if ( typeof value === "object" && value !== null ) {
			if ( seen.has( value ) ) return "[Circular]";
			seen.add( value );
		}
			return value;
		});
		const utf8_bytes = new TextEncoder().encode( safe_string );
		const binary_str = Array.from( utf8_bytes , byte => String.fromCharCode( byte ) ).join( '' );
		return btoa( binary_str );
	}

	let pdf_elements = document.querySelectorAll( 'a.card-link[href^="../lectures/"][href$=".pdf"]' );
	let pdf_urls = [ ...pdf_elements ].map( x => x.href );
	let json_b64 = base64_encode( pdf_urls );
	console.log( json_b64 );

})();