Breakdown of movies released commercially in NYC since '98

nycreleases.txt

1998: 471
1999: 472
2000: 461
2001: 453
2002: 489
2003: 480
2004: 549
2005: 592
2006: 643
2007: 647
2008: 645
2009: 607
2010: 655
2011: 786

Average: 568

Source: http://www.panix.com/~dangelo

tabulator.py

import re, urllib2

s = ['98','99','00','01','02','03','04','05','06','07','08','09','10','']
t = []

for year in s:
    u = "http://www.panix.com/~dangelo/nymaster%s.html" % str(year)
    html = urllib2.urlopen(u).read()
    html = html.split('<b>Week of', 1)[1]
    html = re.sub('\n\n', '\n', html)
    html = re.sub('(\n|^)<br> <hr>\n', '\n', html)
    html = re.sub('\n<hr>\n', '\n', html)
    html = re.sub('\n<br>\n', '\n', html)
    html = re.sub('\n<b>Week of.*\n', '\n', html)
    html = html.split('\n', 1)[1]
    html = html.rsplit('\n', 1)[0]
    if year.startswith('9'):
        y = "19" + str(year)
    elif year != '':
        y = "20" + str(year)
    else:
        y = "2011"
    c = len(html.split('\n'))
    print "%s: %s" % (y, c)
    t.append(c)

print ""
print "Average: %s" % int(round(float(sum(t)) / len(t)))
print ""
print "Source: http://www.panix.com/~dangelo"