python爬取双色球历史数据_爬取双色球历史数据

爬取双色球历史数据

爬去地址：http://baidu.lecai.com/lottery/draw/list/50

需要的包：BeautifulSoup install

脚本如下 运行后生成的数据json处理后存在data文件中

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

import urllib

import re

import json

from bs4 import BeautifulSoup

li = []

for year in range(2003, 2015):

print year

htmlcon = urllib.urlopen('http://baidu.lecai.com/lottery/draw/list/50?d=%s-01-01' % year)

html = htmlcon.read()

htmlcon.close()

soup = BeautifulSoup(html)

table_html_set = soup.findAll(id='draw_list')

num_tuple_list = []

for table_html in table_html_set:

tr_html_set = table_html.findAll('tr')

for tr_html in tr_html_set:

span_html_set = tr_html.findAll('span', attrs={'class': re.compile('^ball_')})

num_