LoL Champion info scraper

scraper.py

from bs4 import BeautifulSoup
import requests
import re
import json

base_url = 'http://na.leagueoflegends.com/'
get_page = lambda x: BeautifulSoup(requests.get(base_url + x).text)


# step one, get a list of all champion urls
print 'getting list of urls'
soup = get_page('/champions/')

champion_urls = map(
    lambda x: x['href'],
    soup.select('#champions_grid_view a.lol_champion')
)

print 'urls acquired'
# now, grab the info for each champ and make a list of dicts
champions = []
i = 0

for champ_url in champion_urls:
    soup = get_page(champ_url)

    champion = {
        'id': int(re.search(r'(\d+)', champ_url).group(0)),
        'name': soup.select(".champion_name")[0].text,
        'title':  soup.select(".champion_title")[0].text,
        'description': soup.select(".champion_description")[0].text,
        'stats': {},
    }
    for stat in soup.select('.stats_table tr'):
        name = stat.select('.stats_name')[0].text.lower()
        champion['stats'][name] = {}

        champion['stats'][name]['base'] = float(stat.select('.stats_value')[0].text)

        try:
            champion['stats'][name]['per_level'] = float(re.search(
                r'([+-]\d+)',
                stat.select('.ability_per_level_stat')[0].text
            ).group(0))
        except:
            champion['stats'][name]['per_level'] = 0

    champions.append(champion)
    i += 1
    print "champion %d/%d -- %s is scraped" % (
        i,
        len(champion_urls),
        champion['name']
    )
    

print json.dumps(champions)