blob: 2d9b4cd7457ea1eb0a5ea851db41650b2ad057bd (
plain)
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
|
#!/usr/bin/env python
import urllib
import urllib2
import urlparse
from lxml import html
for year in range(1954,2015):
url = 'http://chicanef1.com/calendar.pl?' + urllib.urlencode({'year':year,'nc':0})
contents = urllib2.urlopen(url).read()
tree = html.fromstring(contents)
links = tree.xpath('//table[@cellpadding=6]//tr/td[1]//a')
for link in links:
url = urlparse.urlparse(link.attrib['href'])
url = url._replace(path='race.pl')
query = dict(urlparse.parse_qsl(url.query))
for type in ['qual', 'preq']:
query['type'] = type
url = url._replace(query=urllib.urlencode(query))
print urlparse.urljoin('http://chicanef1.com', urlparse.urlunparse(url))
|
