curunir/modules/mensa.py

# -*- coding: utf-8 -*-

from . import ModuleBase
import re
from datetime import datetime, date, timedelta, time
import urllib

class Module(ModuleBase):
    def __init__(self, manager):
        ModuleBase.__init__(self, manager)
    
    def commands(self):
        return [('!mensa [tomorrow]', 'Zeigt das aktuelle Menü der Mensa der Uni Lübeck an (oder das des nächsten Tages)')]
    
    def groupchat(self, room, nick, text, handler):
        if not re.match(r'!mensa(?:\W|\Z)', text):
            return
        
        tomorrow = re.match(r'!mensa\W+tomorrow(\W|\Z)', text)
        daystr = 'Heute'
        day = date.today()
        if tomorrow or datetime.now().time() > time(15):
            day += timedelta(1)
            daystr = 'Morgen'
        datestr = day.strftime(r'%d\.%m\.<\/div>')
        
        try:
            f = urllib.urlopen(self.manager.config['mensa_url'], 'r')
            data = f.read()
            f.close()
        except IOError:
            handler.reply('Hmm, es scheint gerade keine Daten über das Mensa-Menü zu geben.')
            return
        
        def handle_data(data):
            if not re.search(datestr, data):
                return False
            
            match = re.compile(r'^.*' + datestr + r'(.*?)(?:<td rowspan="3" class="schrift_fett"><div>|</table>).*$', re.DOTALL).match(data)
            
            if not match:
                return False
            
            data = match.group(1)
            
            r = re.compile(r'.*?<tr[^>]*>(.*?)</tr>', re.DOTALL)
            r2 = re.compile(r'(?:.*?<td[^>]*>(.*?)</td>){4}', re.DOTALL)
            
            mealstr = ''
            pos = 0
            while not r2.match(mealstr):
                match = r.match(data, pos)
                if not match:
                    return False
                mealstr = match.group(1)
                pos = match.end()
            
            match = r.match(data, pos)
            if not match:
                return False
            pricestr = match.group(1)
            
            meals = []
            pos = 0
            r = re.compile(r'\s*<td class="schrift_(gerichte|spezial)">(.+?)</td>', re.DOTALL)
            match = r.match(mealstr, pos)
            while match:
                meals.append(match.group(2))
                
                if len(meals) >= 4:
                    break
                
                pos = match.end()
                match = r.match(mealstr, pos)
            
            if len(meals) < 4:
                return False
            
            prices = []
            pos = 0
            r = re.compile(r'\s*<td class="schrift_(?:preise|spezial)">(.+?)</td>', re.DOTALL)
            match = r.match(pricestr, pos)
            while match:
                prices.append(match.group(1))
                
                if len(prices) >= 4:
                    break
                
                pos = match.end()
                match = r.match(pricestr, pos)
            
            if len(prices) < 4:
                return False
            
            def unescape(s):
                s = s.replace('&nbsp;', '')
                s = s.replace('&euro;', '€')
                s = s.replace('&auml;', 'ä')
                s = s.replace('&Auml;', 'Ä')
                s = s.replace('&ouml;', 'ö')
                s = s.replace('&Ouml;', 'Ö')
                s = s.replace('&uuml;', 'ü')
                s = s.replace('&Uuml;', 'Ü')
                s = s.replace('&szlig;', 'ß')
                s = s.replace('&amp;', '&')
                s = s.replace('&lt;', '<')
                s = s.replace('&gt;', '>')
                s = s.replace('&quot;', '"')
                s = s.replace('&ldquo;', '“')
                s = s.replace('&bdquo;', '„')
                s = s.replace('<br />', ' ')
                s = re.sub(r'-\s+', '-', s)
                s = re.sub(r'\s+', ' ', s)
                s = re.sub(r'([a-zäöüß])-([a-zäöüß])', r'\1\2', s)
                s = re.sub(r'<img[^>]*logo_bio[^>]*>', 'Bio', s)
                s = re.sub(r'<[^>]*>', '', s)
                return s
            
            meals = map(unescape, meals)
            prices = map(unescape, prices)
            
            reply = 'Mensa-Menü für den %s\n\n' % day.strftime('%d.%m.%y')
            if meals[0]:
                reply += 'Eintopf: %s (%s)\n' % (meals[0].strip(), prices[0].strip())
            if meals[1]:
                reply += 'Hauptgericht 1: %s (%s)\n' % (meals[1].strip(), prices[1].strip())
            if meals[2]:
                reply += 'Hauptgericht 2: %s (%s)\n' % (meals[2].strip(), prices[2].strip())
            if meals[3]:
                reply += 'Vegetarisches Hauptgericht: %s (%s)\n' % (meals[3].strip(), prices[3].strip())
            
            return reply
        
        reply = handle_data(data)
        if not reply:
            reply = '%s kein Mensa-Menü... ist vielleicht Wochenende?' % daystr
        
        handler.reply(reply.strip())