Journey to the West (西游记) character count

xyj-count.py

'''
Count the number of characters in Journey to the West
'''

import urllib2

URL = 'http://www.sdmz.net/xy/%03d.htm'
CHAPTERS = 100

def do_count():
    chars = set()
    for n in xrange(1, CHAPTERS + 1):
        print 'Chapter', n
        chars = chars.union(urllib2.urlopen(URL % n).read().decode('gb2312', 'ignore'))
        print len(chars)

if __name__ == '__main__':
    do_count()