Yahoo!競馬の情報から直近5走のデータを取得して縦馬柱をipythonで表示する

gistfile1.py

import pandas as pd
from lxml import html

# 出馬表
denma_url = 'http://keiba.yahoo.co.jp/race/denma/1405040911/'
xpath = '//table'
denma_tree = html.parse(denma_url)
denma_table = denma_tree.xpath(xpath)[2]
denma_html = html.tostring(denma_table)
denma_html = denma_html.decode('utf-8').replace('<br>', '\\n')
denma = pd.read_html(denma_html, header=0)[0]
denma_table.make_links_absolute()

# 各馬の出走レース履歴
hist = []
for uma_url in [x[2].find('a').get('href') for x in denma_table[1:]]:
    uma_tree = html.parse(uma_url)
    uma_table = uma_tree.xpath(xpath)[6]
    f = """{0} {2}
{1}
{10} {5}頭 {7}番 {8}人
{13}kg {11} {12}
{3} {4} {14}
{16} {15}F
({17})"""
    hist.append([f.format(*[col.text_content() for col in row]) for row in
                 uma_table[1:6]])
hist = pd.DataFrame(hist, columns=['前走', '前々走', '3走前', '4走前', '5走前'])

# 縦馬柱
bachu = pd.concat([denma, hist.iloc[:, ::-1]], axis=1).T

# ipython notebookで表示
from IPython.display import HTML

pd.set_option('display.max_colwidth', 1000)
HTML(bachu.to_html(classes='bachu').replace('\\n', '<br>'))