python预测彩票模型_python预测下一期双色球号码【机器学习】

Task：

1. 在福彩官网抓取所有的历史双色球数据。

2. 使用历史数据进行继续学习。

Part1 数据抓取

main.pyimport re

from bs4 import BeautifulSoup

import urllib2

from mylog import MyLog as mylog

from save2excel import SavaBallDate

class DoubleColorBallItem(object):

date = None

order = None

red1 = None

red2 = None

red3 = None

red4 = None

red5 = None

red6 = None

blue = None

money = None

firstPrize = None

secondPrize = None

class GetDoubleColorBallNumber(object):

'''这个类用于获取双色球中奖号码， 返回一个txt文件

'''

def __init__(self):

self.urls =

self.log = mylog()

self.getUrls()

self.items = self.spider(self.urls)

self.pipelines(self.items)

self.log.info('beging save data to excel \r\n')

SavaBallDate(self.items)

self.log.info('save data to excel end ...\r\n')

def getUrls(self):

'''获取数据来源网页

'''

URL = r'http://kaijiang.zhcw.com/zhcw/html/ssq/list_1.html'

htmlContent = self.getResponseContent(URL)

soup = BeautifulSoup(htmlContent, 'lxml')

tag = soup.find_all(re.compile('p'))[-1]

pages = tag.strong.get_text()

for i in xrange(1, int(pages)+1):

u