Ordnet alten Prüfungsleistungen der PO2004 die neuen der PO2009 zu. Für die Leibniz Uni Hannover.

Po04toPo09.py

from collections import namedtuple, defaultdict
from pprint import pprint
from lxml import html

import csv

Info = namedtuple('Info', 'new old')

def parse_mapping(tree):
    mapping = defaultdict(list)
    rows = tree.xpath('//tr')
    for row in rows[1:]:
        try:
            modul_tag, prfn_tag = row[0].cssselect('small')
        except ValueError:
            continue
        old = {}
        old['modul'] = modul_tag.text.rstrip(':')
        old['name'] = row[0][1].tail
        old['prfn'] = prfn_tag[0].text.split(': ')[1]
        new = {}
        new_td = row[2]
        new['kompetenz'] = new_td[0].text.rstrip(' - ')
        new['modul'] = new_td[0][0].tail.strip().rstrip(':')
        try:
            new['name'] = new_td.cssselect('b')[1].text
        except IndexError:
            new['name'] = new_td[1].tail
        if new['name'] is None:
            continue
        new['prfn'] = new_td.cssselect('small > i')[0].text.split(': ')[1]

        mapping[old['prfn']].append(Info(new=new, old=old))

    return mapping


def write_mapping(mapping, filename='mapping.csv'):
    with open(filename, 'w', newline='') as out:
        writer = csv.writer(out)
        writer.writerow(['Alte Prüfungsnummer', 'Altes Modul',
                         'Alter Name', 'Prüfungsnummer', 'Kompetenzbereich', 'Name'])
        for prfn in sorted(mapping.keys()):
            for info in mapping[prfn]:
                old, new = info.old, info.new
                writer.writerow([old['prfn'], old['modul'], old['name'], new['prfn'], new['kompetenz'], new['name']])


# noten.csv is in my case the qis-notespiegel html page, parsed with LibreOffice and saved as a single csv
with open('noten.csv') as noten:
    reader = csv.reader(noten, delimiter=',')
    errors = []
    duplicates = defaultdict(list)
    # mapping.html ist von http://www.dbs.uni-hannover.de/fbinf/modkat/mapping.php
    tree = html.parse('mapping.html')
    mapping = parse_mapping(tree)
    row_mapping = {}
    filtered_mapping = {}
    for row in reader:
        if len(row) > 2:
            prfn, name, note, best, cp, _ = row
            try:
                if prfn in filtered_mapping:
                    duplicates[prfn].append(row_mapping[prfn])
                    duplicates[prfn].append(row)
                filtered_mapping[prfn] = mapping[prfn]
                row_mapping[prfn] = row
            except KeyError:
                errors.append(row)

    write_mapping(filtered_mapping, 'result.csv')

    print('not found: ')
    print(errors)
    print('duplicates: ')
    for items in duplicates.items():
        pprint(items)