Scrape unicode.org

# import urllib2
# import urllib
from bs4 import BeautifulSoup
from binascii import a2b_base64

gmail = 11
softbank = 12
docomo = 13
kddi = 14

font = docomo
ext = '.png'
# url = 'http://unicode.org/emoji/charts/full-emoji-list.html'
contents = open('emojitable.html','r').read()
soup = BeautifulSoup(contents)
tbody = soup.find("tbody")
for row in tbody.findAll('tr'):
    #first_column = row.findAll('th')[0].contents
    uni = ""
    sb = ""
    columns = row.findAll('td')
    if len(columns) > 0:
        uni = columns[1].a.contents[0].replace('U+','').replace(' ','_')
        sbc = columns[font]
        if sbc.contents is not '\u2014':
            if sbc.img is not None:
                sb = sbc.img['src']
                if sb is not None:
                    binary_data = a2b_base64(sb.replace('data:image/png;base64,',''))
                    fd = open('rip/'+uni+ext, 'wb')
                    fd.write(binary_data)
                    fd.close()
                    #print uni, sb