scrape.py

import re
import urllib2
import itertools
import codecs

def download(url):
	print "Downloading: ", url
	try:
		html = urllib2.urlopen(url).read()
	except urllib2.URLError as e:
		print "Download Error: ", e.reason
		html = None
	return html



baseurl = 'http://www.euroleague.net/main/results/showgame?gamecode=%d&seasoncode=E2018'

hdr = {'User-Agent': 'Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.11 (KHTML, like Gecko) Chrome/23.0.1271.64 Safari/537.11',
       'Accept': 'text/html,application/xhtml+xml,application/xml;q=0.9,*/*;q=0.8',
       'Accept-Charset': 'ISO-8859-1,utf-8;q=0.7,*;q=0.3',
       'Accept-Encoding': 'none',
       'Accept-Language': 'en-US,en;q=0.8',
       'Connection': 'keep-alive'}

#for page in itertools.count(1):
for page in range(25,33):
	url = baseurl % page
	print page, url

	try:
		req = urllib2.Request(url, headers=hdr)
		print "requested"
		req = urllib2.urlopen(req)
		print "Opened"
		content = req.read()
		print "Read"
		encoding=req.headers['content-type'].split('charset=')[-1]
		ucontent = unicode(content, encoding)
	except urllib2.URLError as e:
		print "Download Error: ", e.reason
		content = None
		req = None
		ucontent = None

	if ucontent is None:
		print "Fail! ", page
	else:
		print "Success! ", page 
		f = "games/game-%d.txt" % page
		with codecs.open(f, 'w', 'utf-8') as fout:
			fout.write(ucontent)