Cap 10k parsing script

extract.py

from bs4 import BeautifulSoup
#produce tab delimited CSV files from large html files
for year in range(2008, 2013):
	print 'processing ' + str(year)
	file = str(year) + '.html'
	f = open(file, 'r');

	html = f.read()
	soup = BeautifulSoup(html)
	table = soup.find("table")	

	#first row with column titles
	rows = table.findAll('tr')

	i = 0
	#write data to csv file
	outfile = str(year) + '.csv'
	out = open(outfile, 'w')
	this_row = ''
	for row in rows:
		cols = row.findAll('td')
		for col in cols:
			b = col.find('b')
		
			text = str(b.string)
			this_row += text
			this_row += '	'

		if i % 2 == 0:
			this_row += '\n'
			out.write(this_row)
			this_row = ''
		i += 1
			

	out.close();
	f.close()