crawler.py

# -*- coding: utf- 8 -*-

import os
import urllib
from teams import teams, teams_old

URL = "http://bis.npb.or.jp/%s/stats/id%s1_%s.html"
PATH = "./html/%s_%s_%s.html"

def crawling(year, mode, team):
    url = URL % (year, mode, team)
    path = PATH % (year, mode, team)
    urllib.urlretrieve(url, path)

if __name__ == "__main__":
    if not os.path.exists("html"):
        os.mkdir("html")

    years = range(2005, 2013)
    for year in years:
        print year
        
        if year < 2012:
            ts = teams_old
        else:
            ts = teams
            
        for t in ts:
            crawling(year, 'b', t)
            crawling(year, 'p', t)