ATP rankings scraper

atp3.py

import re
import codecs
import urllib.request
from bs4 import BeautifulSoup
from bs4 import SoupStrainer

start = 'http://www.atpworldtour.com/Rankings/Singles.aspx'
outfile = codecs.open('atp_ranks3.csv', 'w','utf-8')



for strata in range(1,1501,100):
	start = 'http://www.atpworldtour.com/Rankings/Singles.aspx?d=24.06.2013&r=' + str(strata) + '&c=#'
	print (start)

	soup = BeautifulSoup(urllib.request.urlopen(start),parse_only = SoupStrainer('table',{'class':'bioTableAlt stripeMe'}))	
	for therow in soup.find_all('tr')[1:]:
		for thecell in therow.find_all('td'):
			if (thecell.has_key('class') and (thecell['class'][0] == 'first')):
				rank = thecell.find('span')
				rank = rank.get_text()
				name = thecell.find('a')
				name = name.get_text()
				nationality = thecell.get_text()
				nationality = re.search('\([A-Z]{3}\)',nationality)
				nationality = nationality.group()
				outfile.write(rank + '\t' + name + '\t' + nationality + '\t')
			else:
				cellcontents = thecell.get_text().strip()
				cellcontents = re.sub('\n',' ',cellcontents)
				outfile.write(cellcontents + '\t')

		outfile.write('\n')

outfile.close()