Improved mensa module

1 files changed, 101 insertions, 76 deletions

diff --git a/modules/mensa.py b/modules/mensa.py
index 55fa664..40c63fa 100644
--- a/modules/mensa.py
+++ b/modules/mensa.py
@@ -17,99 +17,124 @@ class Module(ModuleBase):
             return
         
         tomorrow = re.match(r'!mensa\W+tomorrow(\W|\Z)', text)
-        daystr = 'heute'
+        daystr = 'Heute'
         day = date.today()
         if tomorrow:
             day += timedelta(1)
-            daystr = 'morgen'
-        datestr = day.strftime('%d.%m.</div>')
+            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
         
-        found = False
-        line = f.readline()
-        while line:
-            if re.search(datestr, line):
-                found = True
-                break
-            line = f.readline()
-        
-        if not found:
-            f.close()
-            handler.reply('%s kein Mensa-Menü... ist vielleicht Wochenende?' % daystr)
-            return
-        
-        meals = []
-        r = re.compile(r'<td class="schrift_gerichte">([^<]*)</td>')
-        line = f.readline()
-        while line:
-            match = r.search(line)
-            if match:
-                meals.append(match.group(1))
+        def handle_data(data):
+            if not re.search(datestr, data):
+                return False
             
-            if len(meals) >= 4:
-                break
+            (data, count) = re.compile(r'^.*' + datestr + r'(.*?)<td rowspan="3" class="schrift_fett"><div>.*$', re.DOTALL).subn(r'\1', data)
             
-            if re.search('<td rowspan="3" class="schrift_fett"><div>', line):
-                break
+            if count < 1:
+                return False
             
-            line = f.readline()
-        
-        prices = []
-        r = re.compile(r'<td class="schrift_preise">([^<]*)</td>')
-        line = f.readline()
-        while line:
-            match = r.search(line)
-            if match:
+            r = re.compile(r'.*?<tr[^>]*>(.*?)</tr>', re.DOTALL)
+            match = r.match(data)
+            if not match:
+                return False
+            mealstr = match.group(1)
+            
+            match = r.match(data, match.end())
+            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), match.group(1) == 'spezial'))
+                
+                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:
-                break
+            if len(prices) < 4:
+                return False
             
-            if re.search('<td rowspan="3" class="schrift_fett"><div>', line):
-                break
+            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('<br />', ' ‒ ')
+                s = re.sub('\s+', ' ', s)
+                return s
             
-            line = f.readline()
-        
-        f.close()
-        
-        if len(meals) < 4 or len(prices) < 4:
-            handler.reply('%s kein Mensa-Menü... ist vielleicht Wochenende?' % daystr)
-            return
-        
-        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 = re.sub('\s+', ' ', s)
-            return s
-        
-        meals = map(unescape, meals)
-        prices = map(unescape, prices)
-        
-        reply = 'Mensa-Menü für den %s\n\n' % day.strftime('%d.%m.%y')
+            meals = map(lambda (s, special): (unescape(s), special), meals)
+            prices = map(unescape, prices)
+            
+            reply = 'Mensa-Menü für den %s\n\n' % day.strftime('%d.%m.%y')
+            if meals[0][0]:
+                if meals[0][1]:
+                    reply += 'Mensatipp: '
+                else:
+                    reply += 'Eintopf: '
+                reply += '%s (%s)\n' % (meals[0][0], prices[0])
+            if meals[1][0]:
+                if meals[1][1]:
+                    reply += 'Mensatipp: '
+                else:
+                    reply += 'Hauptgericht 1: '
+                reply += '%s (%s)\n' % (meals[1][0], prices[1])
+            if meals[2][0]:
+                if meals[2][1]:
+                    reply += 'Mensatipp: '
+                else:
+                    reply += 'Hauptgericht 2: '
+                reply += '%s (%s)\n' % (meals[2][0], prices[2])
+            if meals[3][0]:
+                if meals[3][1]:
+                    reply += 'Mensatipp: '
+                else:
+                    reply += 'Vegetarisches Hauptgericht: '
+                reply += '%s (%s)\n' % (meals[3][0], prices[3])
+            
+            return reply
         
-        if meals[0]:
-            reply += 'Eintopf: %s (%s)\n' % (meals[0], prices[0])
-        if meals[1]:
-            reply += 'Hauptgericht 1: %s (%s)\n' % (meals[1], prices[1])
-        if meals[2]:
-            reply += 'Hauptgericht 2: %s (%s)\n' % (meals[2], prices[2])
-        if meals[3]:
-            reply += 'Vegetarisches Hauptgericht: %s (%s)\n' % (meals[3], prices[3])
+        reply = handle_data(data)
+        if not reply:
+            reply = '%s kein Mensa-Menü... ist vielleicht Wochenende?' % daystr
         
         handler.reply(reply.strip())