競馬 - Yahoo!スポーツ

yahoo_keiba.py

#!/usr/bin/env python
# -*- coding: utf-8 -*-

import sys
import os
from subprocess import *
import urllib2,re,math
from BeautifulSoup import BeautifulSoup

def get_races(url,r=10):
    ''' url:馬情報のURL r:解析対象レース数 '''
    opener = urllib2.build_opener()
    # html 取得
    html = opener.open(url).read()
    
    # テーブル取得
    soup = BeautifulSoup(html)
    tables = soup.findAll('table')
    races = tables[6]
    races = races.findAll('tr')
    
    p = re.compile('''<("[^"]*"|'[^']*'|[^'">])*>''')
    
    uma = []
    for race in races[:r]:
        cols = race.findAll('td')
        if len(cols)>2:
            uma += [[ p.sub('', str(col)).strip() for col in cols ]]

    return uma

def get_uma_links(denma_id):
    opener = urllib2.build_opener()
    # トップページ
    top = "http://keiba.yahoo.co.jp"
    
    # 出馬表
    # 09 08         05 04 11
    # 年 開催競馬場 回 日 レース
    url = top + '/race/denma/%s/' % denma_id
    print url
    
    # 出馬表取得
    html = opener.open(url).read()
    
    # HTML解析
    soup = BeautifulSoup(html)
    tables = soup.findAll('table')
    
    # 各馬へのリンクの取得
    denma = tables[2]
    links = denma.findAll('a', href=lambda value: value and 'horse' in value)
    links = [(top + link['href'],link.strong.string) for link in links]
    
    # 馬データの取得
    return links

def main():
    # ヘッダ
    heads = '年月日,レース,競馬場,コース,馬場,頭数,枠番,馬番,人気,オッズ,着順,騎手名,斤量,馬体重,タイム,上3F,通過順位,タイム差'.split(',')
    for link, uma in get_uma_links('1006040411'):
        print uma, link
        print
        for race in get_races(link):
            race = dict(zip(heads,race))
            for k, v in race.iteritems():
                print "%s:%s" % (k, v)
            print

if __name__ == '__main__':
    main()