OkusonParser LAInf18 Needs https://jsoup.org/packages/jsoup-1.11.2.jar in the same path

buildOkusonParser.sh

javac -cp .:jsoup-1.11.2.jar OkusonParser.java

downloadscript.sh

#!/bin/bash
echo Matrnr:
read matrnr
echo Password:
read -s pass
pass=$(echo -e "import urllib.parse\nprint(urllib.parse.quote_plus('$pass'))" | python3)
for i in `seq 1 9`; do
	wget "https://www2.math.rwth-aachen.de/LAInf18/QuerySheet?id=$matrnr&passwd=$pass&format=MathJax&resolution=Standard&sheet=$i" -O sheet$i.html
done
exit

OkusonParser.java

import org.jsoup.Jsoup;
import org.jsoup.nodes.Document;
import org.jsoup.nodes.Element;
import org.jsoup.select.Elements;
import java.io.File;
import java.nio.charset.StandardCharsets;
import java.io.IOException;
import java.nio.file.Files;
import java.util.*;

public class OkusonParser {

	public static void main(String[] args) throws Exception {
		if (args.length < 1) {
			System.out.println("Usage: java OkusonParser [Sheet-Folder-1] ... [Sheet-Folder-n]\n\n" +
					"In each sheet-folder have to be only files named sheetXX.html, and the same amount in each folder.\n" +
					"Use downloadskript.sh to download them properly instead of through the browser.\n");
			return;
		}
		File init = new File(args[0]);
		if (!init.isDirectory()) {
			System.err.println(args[0]+" is not a directory!");
			return;
		}
		String[] initf = init.list();
		if (initf == null) {
			System.err.println("Error reading "+args[0]+".");
			return;
		}
		// Parse the input folders to Strings:
		int sheets = initf.length;
		String input[][] = new String[args.length][sheets];

		File[][] files = new File[args.length][sheets];
		for (int i = 0; i< args.length; i++) {
			File cur = new File(args[i]);
			File[] cure  = cur.listFiles();
			if (!cur.isDirectory()) {
				System.err.println(args[i]+" is not a directory!");
				return;
			}
			if ( cure == null) {
				System.err.println("Can't list files on folder "+args[i]+"!");
				return;
			}
			if (cure.length != sheets) {
				System.err.println("Sheet folder \""+args[i]+"\" has a different amount of files than \""+args[0]+"\"!");
				return;
			}
			files[i] = cure;
			Arrays.sort(files[i]);
		}
		for (int i = 0; i< args.length; i++) {
			for(int j = 0; j< sheets; j++) {
				input[i][j] = preProcessRules(readFile(files[i][j]));
			}
		}


		// Parse the input files into Objects, with no duplicate questions
		Blatt[] blaetter = new Blatt[sheets];
		for(int j = 0; j< sheets; j++) {
			blaetter[j] = new Blatt(files[0][j].getName().replace("sheet","").replace(".html",""));
		}

		for (int i = 0; i< args.length; i++) {
			for(int j = 0; j< sheets; j++) {
				Document doc = Jsoup.parse(input[i][j]);
				Elements elements = doc.body().select("*");
				String currentaufgabe = "";
				String currentquestion = "";
				boolean newquestion = true;
				for (Element element : elements) {
					switch(element.className()) {
						case "hidden":
							String curhead = element.text().replace("\\(","").replace("\\)","");
							if (!header.contains(curhead))
								header += "\n"+curhead+"\n";
							break;
						case "number":
						case "exnr":
							currentaufgabe = element.text();
							if (!blaetter[j].aufgaben.containsKey(currentaufgabe)) {
								blaetter[j].aufgaben.put(currentaufgabe,new Aufgabe());
							}
							break;
						case "intro":
						case "extext":
							if (blaetter[j].aufgaben.get(currentaufgabe).aufgabentext == null) {
								blaetter[j].aufgaben.get(currentaufgabe).aufgabentext = element.text();
							}
							break;
						case "question":
							if (!blaetter[j].aufgaben.get(currentaufgabe).subaufgaben.containsKey(element.text())) {
								currentquestion = element.text();
								blaetter[j].aufgaben.get(currentaufgabe).subaufgaben.put(currentquestion,"");
								newquestion = true;
							} else {
								newquestion = false;
							}
							break;
						case "erg":
							if (newquestion) {
								blaetter[j].aufgaben.get(currentaufgabe).subaufgaben.put(currentquestion,element.text());
							}
							break;
					}
				}
			}
		}

		//Parse the objects into a latex file
		StringBuilder out = new StringBuilder();
		out.append(header);
		out.append(begin);
		for (Blatt b : blaetter) {
			out.append(String.format("\\section{Blatt %s}\n",b.blattnummer));
			for (String aufgabennummer : b.aufgaben.keySet()) {
				out.append(String.format("\\subsection{Aufgabe %s}\n",aufgabennummer));
				out.append(b.aufgaben.get(aufgabennummer).aufgabentext);
				out.append("\n\\begin{itemize}\n");
				int j = 0;
				for (String sub : b.aufgaben.get(aufgabennummer).subaufgaben.keySet()) {
					out.append("\n\\item ");
					out.append(sub);
					out.append("\n");
					if (j<b.aufgaben.get(aufgabennummer).subaufgaben.size())
						out.append(String.format("\\newline\\fbox{\\parbox{0.9\\textwidth}{Solution: %s}}",b.aufgaben.get(aufgabennummer).subaufgaben.get(sub)));
				}
				out.append("\n\\end{itemize}\n");
			}
		}
		out.append("\n\\end{document}");
		System.out.println(postProcessRules(out.toString()));
	}

	public static class Aufgabe {
		String aufgabentext;
		Map<String,String> subaufgaben;

		public Aufgabe () {
			subaufgaben = new TreeMap<>();
		}
	}

	public static class Blatt {
		String blattnummer;
		Map<String, Aufgabe> aufgaben;

		public Blatt (String bn) {
			blattnummer = bn;
			aufgaben = new TreeMap<>();
		}
	}

	private static String readFile(File file) throws IOException {
		byte[] encoded = Files.readAllBytes(file.toPath());
		return new String(encoded, StandardCharsets.UTF_8);
	}

	private static String postProcessRules(String prefinal) {
		return prefinal.replace("verbatim}\\","verbatim}")
						.replace("\\begin{itemize}\n\n\\end{itemize}","");
	}

	private static String preProcessRules(String init) {
		return init.replace("</p>\n","</p>\\\\\n")
					.replace("\\\\%","\\\\")
					.replace("<code>","\\verb|")
					.replace("</code>","|")
					.replace("{};","{ };")
					.replace("{}","\\{\\}")
					.replace("<ol>","\\begin{enumerate}[label=(\\alph*)]")
					.replace("<ul>","\\begin{enumerate}[label=(\\roman*)]")
					.replace("</ol>","\\end{enumerate}")
					.replace("</ul>","\\end{enumerate}")
					.replace("<dt>","\\textbf{")
					.replace("</dt>","}")
					.replace("<li>","\\item ")
					.replace("</li>","")
					.replace("<em>","\\textit{")
					.replace("</em>","}")
					.replace("\\newcommand{\\ExpandedCoefficientMatrix}[2]{<![CDATA[\\left( \\!\\!\\! \\begin{array}{c|c} {#1} & {#2} \\end{array} \\!\\!\\! \\right)]]>}","\\newcommand{\\ExpandedCoefficientMatrix}[2]{\\left( \\!\\!\\! \\begin{array}{c|c} {#1} & {#2} \\end{array} \\!\\!\\! \\right)]}")
					.replace("<p>[","<p>$[$")
					.replace("]</p>","$]$</p>")
					.replaceAll("(?m)%.*$","");
	}

	private static String header = "\\documentclass[12pt,a4paper]{article}\n"
		+"\\usepackage[utf8]{inputenc}\n"
		+"\\usepackage[german]{babel}\n"
		+"\\usepackage{amsmath}\n"
		+"\\usepackage{amsfonts}\n"
		+"\\usepackage{amssymb}\n"
		+"\\usepackage{amsthm}\n"		
		+"\\usepackage{mathtools}\n"
		+"\\usepackage{enumitem}\n"
		+"\\usepackage[top=1in, bottom=1.25in, left=1.25in, right=1.25in]{geometry}\n"
		+"\\usepackage{hyperref}\n"
		+"\\usepackage{tikz}\n"
		+"\\usepackage{pb-diagram}\n"
		+"\\usetikzlibrary{arrows.meta,positioning,calc}\n"
		+"\\tikzset{graph node/.style={circle,fill=black,draw,minimum size=5pt,inner sep=0pt},node distance=1.5cm and 1.5cm,graph/.style={ }}\n"
		+"\\newcommand{\\n}{~\\\\}\n";

	private static String begin = "\n\\title{TITEL}\n"
		+"\\author{der boy der g, sick wie leukaemie}\n"
		+"\\begin{document}\n"
		+"\\maketitle\n"
		+"\\setcounter{secnumdepth}{0}\n";
}

OkusonParser.sh

java -cp .:jsoup-1.11.2.jar OkusonParser $@