Nobel Banquet Menus

from bs4 import BeautifulSoup as bs
import requests
import io

# Scrape the Nobel website to get data on what was served at the Nobel banquets. 
# Can be turned into word clouds via Tagxedo

def get_result(year):

    result = requests.get('http://www.nobelprize.org/ceremonies/menus/menu-%4i.html' % year)

    return result

def menus(year=1901):

    result = get_result(year)
    content = result.content

    soup = bs(content)

    centered = soup.find_all('div',{'align':'center'})
    c0 = centered[0]

    menu_str = []
    vins_str = []

    if year in (1948,1949,1989):
        menu = c0.find_all('p')[0]
        vins = c0.find_all('p')[2]
    elif year > 2008:
        menu = c0.find_all('p')[1]
        vins = c0.find_all('p')[2]
    else:
        menu = c0.find_all('p')[0]
        vins = c0.find_all('p')[1]

    for m in menu.stripped_strings:
        menu_str.append(' '.join(m.split()))

    for v in vins.stripped_strings:
        vins_str.append(' '.join(v.split()))

    mstr = ' '.join(menu_str)
    vstr = ' '.join(vins_str[1:])

    # Data format changes for 2004 and later

    # All food in the first child; wines separated
    if year > 2003 and year < 2009:
        vins = c0.find_all('p')[1:]
        vins_str = []
        for vv in vins:
            for v in vv.stripped_strings:
                vins_str.append(' '.join(v.split()))
        vstr = ' '.join(vins_str[1:]).split('Translation')[0]

    # Food in the second child; wines separated
    if year == 2009:
        vins = c0.find_all('p')[2:]
        vins_str = []
        for vv in vins:
            for v in vv.stripped_strings:
                vins_str.append(' '.join(v.split()))
        vstr = ' '.join(vins_str[1:]).split('Translation')[0]

    # Food in the first six children, now separated by dish
    if year > 2009:
        menu = c0.find_all('p')[:6]
        menu_str = []
        for vv in menu:
            for v in vv.stripped_strings:
                menu_str.append(' '.join(v.split()))
        mstr = ' '.join(menu_str)
        vins = c0.find_all('p')[6:]
        vins_str = []
        for vv in vins:
            for v in vv.stripped_strings:
                vins_str.append(' '.join(v.split()))
        vstr = ' '.join(vins_str[1:]).split('Translation')[0]

    return mstr,vstr

def get_all(verbose=False):

    years = range(1901,2014,1)

    # Banquet not held during WWI or WWII, as well as a couple of others; remove those years
    bad_years = range(1914,1920) + range(1939,1945) + [1907,1923,1924]
    years_good = filter(lambda y: y not in bad_years, years)

    m_all,v_all = [],[]
    for y in years_good:
        m,v = menus(year=y)
        if verbose:
            print '\nYear %4i' % y
            print 'Menu: %s' % m
            print 'Vins: %s' % v
        m_all.append(m)
        v_all.append(v)

    all_menu = ' '.join(m_all)
    all_vins = ' '.join(v_all)

    # Write to file

    with io.open('/Users/willettk/python/data/nobel_menus.txt','w',encoding='utf8') as f:
        f.write(all_menu)

    with io.open('/Users/willettk/python/data/nobel_vins.txt','w',encoding='utf8') as f:
        f.write(all_vins)

    return None

if __name__ == "__main__":
   get_all()