Extract UEFA rankings for football team ranks from a HTML table

extractranks.py

#!/usr/bin/python
# -*- coding: utf-8 -*-

from lxml import html,etree
import requests
import unicodecsv

def group(iterator, count):
	itr = iter(iterator)
	while True:
		yield [itr.next() for i in range(count)]

def extractYear(method, year):
	url = 'http://kassiesa.home.xs4all.nl/bert/uefa/data/method' + str(method) + '/trank' + str(year) + '.html'
	page = requests.get(url)
	tree = html.fromstring(page.text)	

	# Team ranks appear in usuaal cells (tr)
	cells = tree.xpath('//table[@class="t1"]//tr/td')
	l = []
	for c in cells:
		l.append(etree.tostring(c).replace('<td>','').replace('<td align="left">','').replace('</td>\n', '').replace('<td/>\n',''))
	ranks = list(group(l,9))
	teamranksFilename = 'data/team-rank-' + str(year) +'.csv'
	with open(teamranksFilename, 'wb') as teamranks:
		teamranks = unicodecsv.writer(teamranks, delimiter=',', encoding='utf-8')
		teamranks.writerows(ranks)

	# Country ranks appear in usuaal cells (tr)
	cells = tree.xpath('//table[@class="t1"]//tr/th')
	l = []
	for c in cells:
		l.append(etree.tostring(c).replace('<th>','').replace('<th align="left">','').replace('</th>\n', '').replace('<th/>\n',''))
	ranks = list(group(l,9))
	countryrankFilename = 'data/country-rank-' + str(year) +'.csv'
	with open(countryrankFilename, 'wb') as countryranks:
		countryranks = unicodecsv.writer(countryranks, delimiter=',', encoding='utf-8')
		countryranks.writerows(ranks)


if __name__=="__main__":
	extractYear(1,1960)
	extractYear(1,1965)
	extractYear(1,1970)
	extractYear(1,1975)
	extractYear(1,1980)
	extractYear(1,1985)
	extractYear(1,1990)
	extractYear(1,1995)
	extractYear(1,1998)
	extractYear(2,2000)
	extractYear(2,2003)
	extractYear(3,2005)
	extractYear(3,2008)
	extractYear(4,2010)
	extractYear(4,2014)