Add campusravita

amica.py

@@ -1,8 +1,5 @@
+import pnalib
 import datetime
-import os
-import urllib.request
-import urllib.error
-import json
 
 restaurant_info = [
   [ "(TaY) Amica Minerva", "http://www.amica.fi/minerva", "", "middle", "http://www.amica.fi/api/restaurant/menu/week?language=fi&restaurantPageId=7381" ],
@@ -21,15 +18,8 @@ def get_restaurants(use_old, week):
         url = info[4]
         temp_fname = "amica_{count}.temp.js".format(count = count)
         url = "{url}&weekDate={week_date}".format(url=url, week_date=week_date)
-        if not use_old or not os.path.isfile(temp_fname):
-            try:
-                urllib.request.urlretrieve(url, temp_fname)
-            except urllib.error.HTTPError as e:
-                print("Failed to download {url}".format(url=url))
-        try:
-            with open(temp_fname, "r", encoding="utf-8") as fin:
-                data = json.load(fin)
-        except OSError as e:
+        data = pnalib.get_json_file(url, temp_fname, use_old)
+        if not data:
             continue
 
         week_foods = {}

campusravita.py

@@ -0,0 +1,173 @@
+import pnalib
+import html.parser
+import re
+
+url = "http://www.campusravita.fi/ruokalista";
+
+restaurant_info = [
+  [ "(TAMK) Campus Food", url, "", "middle" ],
+]
+
+class Tracker(object):
+
+    def __init__(self, tag, attr_match=None, on_started=None, on_ended=None, on_data=None):
+        self.tag = tag
+        self.attr_match = attr_match
+        self.on_started = on_started
+        self.on_ended = on_ended
+        self.on_data = on_data
+        self.nesting = 0
+
+    def handle_starttag(self, tag, attrs):
+        if self.tag == tag:
+            if self.nesting:
+                self.nesting += 1
+            else:
+                attrs_matched = False
+                if self.attr_match is None:
+                    attrs_matched = True
+                else:
+                    for attr in attrs:
+                        if attr[0] == self.attr_match[0] and self.attr_match[1].match(attr[1]):
+                            attrs_matched = True
+                if attrs_matched:
+                    self.nesting = 1
+                    if self.on_started:
+                        self.on_started()
+
+
+    def handle_endtag(self, tag):
+        if self.nesting and self.tag == tag:
+            self.nesting -= 1
+            if self.nesting == 0 and self.on_ended:
+                self.on_ended()
+
+    def handle_data(self, data):
+        if self.nesting and self.on_data:
+            self.on_data(data)
+
+    def __bool__(self):
+        return self.nesting > 0
+
+class CampusravitaHTMLParser(html.parser.HTMLParser):
+    week_re = re.compile("Ruokalista - Viikko (\d+)")
+    lunch_re = re.compile("Lounas|Deli-lounas")
+
+    def __init__(self):
+        html.parser.HTMLParser.__init__(self)
+        self._trackers = []
+        self.in_h3 = self._register_tracker("h3", on_data=self.handle_h3)
+        # Everything in inside menu
+        self.in_menu = self._register_tracker("section", ("id", "block-system-main"),
+                on_started=self.handle_menu_start, on_ended=self.handle_menu_end)
+        # Date comes after menu
+        self.in_date_display = self._register_tracker("span", ("class", "date-display-single"),
+                on_data=self.handle_date_display)
+        # Lunch element contains one meal
+        self.in_lunch = self._register_tracker("div", ("about", r"/fi/field-collection/field-ruoka-annos/\d+"),
+                on_started=self.handle_lunch_start, on_ended=self.handle_lunch_end)
+        # Next element contains food name 
+        self.in_lunch_food = self._register_tracker("div", ("class", ".*field-name-field-nimi.*"),
+                on_data=self.handle_lunch_food)
+        # Next element contains food allergies
+        self.in_allergy = self._register_tracker("div", ("class", ".*field-name-field-ruokavaliot.*"),
+                on_started=self.handle_allergy_start, on_ended=self.handle_allergy_end)
+        # Next element contains allergy short name
+        self.in_allergy_short = self._register_tracker("div", ("class", ".*field-name-title field-type-ds.*"),
+                on_data=self.handle_allergy)
+        # Next element contains lunch price
+        self.in_lunch_price = self._register_tracker("div", ("class", ".*field-name-field-annoksen-hinta.*"))
+        self.lunch_type_match = False
+        self.lunch = None
+
+        self.week_foods = {}
+
+    def _register_tracker(self, tag, attr_match=None, **kwargs):
+        tracker = Tracker(tag, (attr_match[0], re.compile(attr_match[1])) if attr_match else None, **kwargs)
+        self._trackers.append(tracker)
+        return tracker
+
+    def handle_date_display(self, data):
+        index = -1
+        if "Maanantai" in data:
+            index = 0
+        elif "Tiistai" in data:
+            index = 1
+        elif "Keskiviikko" in data:
+            index = 2
+        elif "Torstai" in data:
+            index = 3
+        elif "Perjantai" in data:
+            index = 4
+        elif "Lauantai" in data:
+            index = 5
+        elif "Sunnuntai" in data:
+            index = 6
+        if index >= 0:
+            self.current_day = []
+            self.week_foods[index] = self.current_day
+
+    def handle_h3(self, data):
+        if self.in_menu:
+            lunch_match = self.lunch_re.match(data)
+            self.lunch_type_match = bool(lunch_match)
+
+    def handle_menu_start(self):
+        print("*********** menu start")
+
+    def handle_menu_end(self):
+        print("*********** menu end")
+
+    def handle_allergy(self, data):
+        data = data.strip()
+        if self.in_allergy and self.in_allergy_short and self.lunch and data:
+            self.lunch["allergies"].append(data) 
+
+    def handle_allergy_start(self):
+        pass
+
+    def handle_allergy_end(self):
+        pass
+
+    def handle_lunch_food(self, data):
+        data = data.strip()
+        if self.lunch and data:
+            self.lunch["food"].append(data)
+
+    def handle_lunch_start(self):
+        if self.lunch_type_match:
+            print("lunch start")
+            self.lunch = {"food": [], "allergies": []}
+
+    def handle_lunch_end(self):
+        if self.lunch:
+            print(repr(self.lunch).encode("cp1252", "ignore"))
+            menu = "{menu} ({allergies})".format(menu=self.lunch["food"][0], allergies=", ".join(self.lunch["allergies"]))
+            self.current_day.append(menu)
+            self.lunch = None
+
+    def handle_starttag(self, tag, attrs):
+        for tracker in self._trackers:
+            tracker.handle_starttag(tag, attrs)
+
+    def handle_endtag(self, tag):
+        for tracker in self._trackers:
+            tracker.handle_endtag(tag)
+
+    def handle_data(self, data):
+        for tracker in self._trackers:
+            tracker.handle_data(data)
+        week_match = self.week_re.match(data)
+        if week_match:
+            self.week = int(week_match.group(1))
+
+def get_restaurants(use_old, week):
+
+    data = pnalib.get_file(url, "campusravita.html", use_old)
+    parser = CampusravitaHTMLParser()
+    parser.feed(data)
+
+    restaurants = [[restaurant_info[0][0], "", parser.week, parser.week_foods, restaurant_info[0]]]
+
+    return restaurants
+

food.py

@@ -9,7 +9,6 @@
 # This is Public Domain
 
 import sys
-print(sys.version)
 
 day_names = [ "Maanantai", "Tiistai", "Keskiviikko", "Torstai", 
 	       "Perjantai", "Lauantai", "Sunnuntai" ]
@@ -17,7 +16,7 @@ day_names = [ "Maanantai", "Tiistai", "Keskiviikko", "Torstai",
 import amica
 import sodexo
 import juvenes
-import pikante
+import campusravita
 
 allergies = [ "M", "L", "VL", "G", "K", "Ve" ]
 allergy_descriptions = {
@@ -43,9 +42,8 @@ this_week = datetime.datetime.now().isocalendar()[1]
 unordered += amica.get_restaurants(use_old, this_week)
 unordered += juvenes.get_restaurants(use_old, this_week)
 unordered += sodexo.get_restaurants(use_old, this_week)
-unordered += pikante.get_restaurants(use_old, this_week)
+unordered += campusravita.get_restaurants(use_old, this_week)
 
-print(unordered)
 
 max_week = 0;
 for r in unordered:
@@ -149,12 +147,16 @@ def write_prefix_header(fout, prefix, day, resources_prefix):
 
 def write_day(day, header, outfname, last_day, restaurants, prefix, resources_prefix):
     with open(outfname, "w", encoding="utf-8") as fout:
+
+
         import types
         def write(self, writable):
             #print("Writing {}: {}".format(type(writable), writable))
             self.write_orig(writable)
         fout.write_orig = fout.write
         fout.write = types.MethodType(write, fout)
+
+
         fout.write(file_header.format(resources_prefix=resources_prefix))
         fout.write("<h1>{header}</h1>\n".format(header=header))
         # print weekday links

juvenes.py

@@ -1,10 +1,8 @@
 # encoding: UTF-8
+import pnalib
 import datetime
-import urllib.request
-import urllib.error
-import json
 import re
-import os
+import json
 
 # last two in order are $kitchen_info_id, $menu_type_id
 restaurant_info = [
@@ -36,18 +34,7 @@ def get_restaurants(use_old, week):
         for weekday in range(1,7):
             url = "http://www.juvenes.fi/DesktopModules/Talents.LunchMenu/LunchMenuServices.asmx/GetMenuByWeekday?KitchenId={kitchen}&MenuTypeId={menutype}&Week={week}&Weekday={weekday}&lang='fi'&format=json".format(kitchen=kitchen, menutype=menutype, week=week, weekday=weekday)
             temp_fname = "juvenes_{count}-{weekday}.temp.js".format(count=count, weekday=weekday)
-            if not use_old or not os.path.isfile(temp_fname):
-                try:
-                    urllib.request.urlretrieve(url, temp_fname)
-                except urllib.error.HTTPError as e:
-                    print("Failed to download {url}".format(url=url))
-                    # Juvenes may fail with error code 500 if food is not available
-            try:
-                with open(temp_fname, "r", encoding="utf-8") as fin:
-                    jsonp = fin.read()
-                data = json.loads(jsonp[1:-2])
-            except OSError as e:
-                continue
+            data = pnalib.get_jsonp_file(url, temp_fname, use_old)
             if data and data["d"] != "null":
                 data = json.loads(data["d"])
                 cur_day_foods = []

pikante.py

@@ -1,10 +1,27 @@
+import pnalib
+import html.parser
+# Pikante does not have any student restaurants at the moment
+
 pikante_url = "http://www.pikante.fi/lounaslistat-pdf";
 
 restaurant_info = [
-  [ "(TAYS) Finn-Medi", "$pky_url", "all", "middle" ],
+  [ "(TAYS) Finnmedin ravintola", "$pky_url", "all", "middle" ],
   [ "(TAYS) Café Olive", "$pky_url", "all", "middle" ],
   [ "(TAYS) Ellipsi", "$pky_url", "all", "middle" ]
 ]
 
+class PikanteHTMLParser(html.parser.HTMLParser):
+    def handle_starttag(self, tag, attrs):
+        pass
+    def handle_endtag(self, tag):
+        pass
+    def handle_data(self, data):
+        pass
+
 def get_restaurants(use_old, week):
+
+    #data = pnalib.get_file(pikante_url, "pikante.html", use_old)
+    #parser = PikanteHTMLParser()
+    #parser.feed(data)
+
     return []

pnalib.py

@@ -0,0 +1,29 @@
+import os.path
+import urllib.request
+import urllib.error
+import json
+
+def get_jsonp_file(url, temp_fname, use_old):
+    return get_file(url, temp_fname, use_old, jsonp_load)
+
+def get_json_file(url, temp_fname, use_old):
+    return get_file(url, temp_fname, use_old, json.load)
+
+def jsonp_load(fp):
+    return json.loads(fp.read()[1:-2])
+
+def read_all(fp):
+    return fp.read()
+
+def get_file(url, temp_fname, use_old, consumer=read_all):
+    if not use_old or not os.path.isfile(temp_fname):
+        try:
+            urllib.request.urlretrieve(url, temp_fname)
+        except urllib.error.HTTPError as e:
+            print("Failed to download {url}".format(url=url))
+            # Juvenes may fail with error code 500 if food is not available
+    try:
+        with open(temp_fname, "r", encoding="utf-8") as fin:
+            return consumer(fin)
+    except OSError as e:
+        pass

sodexo.py

@@ -1,8 +1,5 @@
+import pnalib
 import datetime
-import os
-import urllib.request
-import urllib.error
-import json
 
 restaurant_info = [
   [ "(TaY) Sodexo Linna", "http://www.sodexo.fi/linna", "", "right", 92],
@@ -25,20 +22,12 @@ def get_restaurants(use_old, week):
             timestr = date.strftime("%Y/%m/%d")
             url = "http://www.sodexo.fi/ruokalistat/output/daily_json/{kitchen}/{timestr}/fi".format(kitchen=kitchen, timestr=timestr)
             temp_fname = "sodexo_{count}-{weekday}.temp.js".format(count=count, weekday=weekday)
-            if not use_old or not os.path.isfile(temp_fname):
-                try:
-                    urllib.request.urlretrieve(url, temp_fname)
-                except urllib.error.HTTPError as e:
-                    print("Failed to download {url}".format(url=url))
-            try:
-                with open(temp_fname, "r", encoding="utf-8") as fin:
-                    data = json.load(fin)
-            except OSError as e:
+            data = pnalib.get_json_file(url, temp_fname, use_old)
+            if not data:
                 continue
             current_day_foods = []
             courses = data["courses"]
             for course_info in courses:
-                print(course_info)
                 if course_info["category"] != "Aamupuuro":
                     food = course_info["title_fi"]
                     if "properties" in course_info: