Daily menus for restaurants around the office

balettcipo.py

# http://balettcipo.hu/hu/napi-menu
from lxml import html
from textwrap import dedent
import sys

from base import get_weekday

URL = 'http://balettcipo.hu/hu/napi-menu'


def get_weekly_menu():
    """Return a list of all daily menus for the current week."""
    tree = html.parse(URL)
    nodes = tree.xpath("//table[@class='foodTable']")
    return [dedent(node.text_content()).strip() for node in nodes]

def get_daily_menu(when=None):
    """Return the daily menu for the given weekday (or for the current day if no
    argument is passed).
    
    """
    day = get_weekday(when)
    menus = get_weekly_menu()
    return menus[day]

if __name__ == '__main__':
    if len(sys.argv) > 1:
        when = sys.argv[1]
    else:
        when = None
    print "The daily menu for %s is:" % (when or "today")
    print get_daily_menu(when)

base.py

from datetime import date

def get_weekday(s=None):
    """Given a string representation, return the int corresponding to the weekday.
    
    If no argument is passed, return the current day."""
    if s is None:
        day = date.today().weekday()
        if day > 4:
            raise ValueError('There is no daily menus on weekends.')
        return day
    
    try:
        return {
            'monday': 0, 'mon': 0,
            'tuesday': 1, 'tue': 1,
            'wednesday': 2, 'wed': 2,
            'thursday': 3, 'thu': 3,
            'friday': 4, 'fri': 4,
        }[s.lower()]
    except KeyError:
        raise ValueError('The day "%s" is not supported' % s)

chagall.py

from datetime import date
from HTMLParser import HTMLParser
import sys
from urllib import urlopen
from base import get_weekday

URL = "http://www.chagallcafe.hu/heti-menu/%s"

HU_WEEKDAYS_ASCII = "hetfo kedd szerda csutortok pentek".split()

class ChagallMenuParser(HTMLParser):
    """Parse the page on chagallcafe.hu where the weekly menu is.
    
    It works by looking for a particular header corresponding the day of the week
    and putting all the text that follows it into a temporary variable.
    
    When a particular endtag is found, the content of the temporary variable
    is concatenated and appended to the list of daily menus.
    
    """
    
    def reset(self):
        self.found_title = False
        self.found_ul = False
        self.daily_menus = []
        self.temp_daily = []
        HTMLParser.reset(self)
    
    def handle_starttag(self, tag, attrs):
        # Look for a weekday header
        if tag == 'h2' and dict(attrs).get('class') == "slider_title":
            self.found_title = True
        if self.found_title and tag == 'ul':
            self.found_ul = True
    
    def handle_data(self, data):
        if self.found_title and self.found_ul:
            data = data.strip()
            if data:
                self.temp_daily.append(data)
    
    def handle_endtag(self, tag):
        if self.found_title and tag == 'div':
            self.daily_menus.append('\n'.join(self.temp_daily))
            self.temp_daily = []
            self.found_title = False
        if self.found_ul and tag == 'ul':
            self.found_ul = False


def get_weekly_menu():
    """Return a list of all daily menus for the current week."""
    day = date.today().weekday()
    hu_weekday = HU_WEEKDAYS_ASCII[day]
    html = urlopen(URL % hu_weekday).read()
    p = ChagallMenuParser()
    p.feed(html.decode('utf-8'))
    return p.daily_menus

def get_daily_menu(when=None):
    """Return the daily menu for the given weekday (or for the current day if no
    argument is passed).
    
    """
    day = get_weekday(when)
    return get_weekly_menu()[day]

if __name__ == '__main__':
    if len(sys.argv) > 1:
        when = sys.argv[1]
    else:
        when = None
    print "The daily menu for %s is:" % (when or "today")
    print get_daily_menu(when)

ring.py

from lxml import html
from itertools import dropwhile
from base import get_weekday
import sys

URL = 'http://www.ringcafe.hu/index.php?option=com_content&view=article&id=12&Itemid=2'

WEEKDAYS_HU = u"H\xe9tf\u0151 Kedd Szerda Cs\xfct\xf6rt\xf6k P\xe9ntek".split()



def stripped_lines(txt, splitchar="\n"):
    """Return the lines of the given text, stripped of whitespace."""
    for line in txt.split(splitchar):
        yield line.strip()

def foo(txt):
    DAYS = WEEKDAYS_HU
    lines = dropwhile(lambda l: l != DAYS[0], stripped_lines(txt))
    
    i = 0
    acc = []
    for line in lines:
        if not line:
            continue
        if i < len(DAYS) and line == DAYS[i]:
            if i:
                yield "\n".join(acc)
            acc = []
            i += 1
        else:
            acc.append(line)
    if acc:
        yield "\n".join(acc)

def get_weekly_menu():
    """Return a list of all daily menus for the current week."""
    tree = html.parse(URL)
    content = tree.xpath("//div[@id='page']")[0]
    raw = content.text_content().strip()
    return list(foo(raw))

def get_daily_menu(when=None):
    """Return the daily menu for the given weekday (or for the current day if no
    argument is passed).
    
    """
    day = get_weekday(when)
    return get_weekly_menu()[day]

if __name__ == '__main__':
    if len(sys.argv) > 1:
        when = sys.argv[1]
    else:
        when = None
    print "The daily menu for %s is:" % (when or "today")
    print get_daily_menu(when)