本文實例講述了Python數據分析之獲取雙色球歷史信息的方法。分享給大家供大家參考，具體如下：

每個人都有一顆中雙色球大獎的心，對于技術人員來說，通過技術分析，可以增加中獎幾率，現使用python語言收集歷史雙色球中獎信息，之后進行預測分析。

說明：采用2016年5月15日獲取的雙色球數據為基礎進行分析，總抽獎數1940次。

初級代碼，有些內容比較繁瑣，有更好的代碼，大家可以分享。

#!/usr/bin/python# -*- coding:UTF-8 -*-#coding:utf-8#author:levycui#date:20160513#Description:雙色球信息收集import urllib2from bs4 import BeautifulSoup  #采用BeautifulSoupimport osimport re#偽裝成瀏覽器登陸,獲取網頁源代碼def getPage(href):  headers = {    'User-Agent':'Mozilla/5.0 (Windows; U; Windows NT 6.1; en-US; rv:1.9.1.6) Gecko/20091201 Firefox/3.5.6'  }  req = urllib2.Request(    url = href ,    headers = headers  )  try:    post = urllib2.urlopen(req)  except urllib2.HTTPError,e:    print e.code    print e.reason  return post.read()#初始化url 雙色球首頁url = 'http://kaijiang.zhcw.com/zhcw/html/ssq/list_1.html'#===============================================================================#獲取url總頁數def getPageNum(url):  num =0  page = getPage(url)  soup = BeautifulSoup(page)  strong = soup.find('td',colspan='7')  # print strong  if strong:    result = strong.get_text().split(' ')    # print result    list_num = re.findall("[0-9]{1}",result[1])    # print list_num    for i in range(len(list_num)):      num = num*10 + int(list_num[i])    return num  else:    return 0#===============================================================================#獲取每頁雙色球的信息def getText(url):  for list_num in range(1,getPageNum(url)):  #從第一頁到第getPageNum(url)頁    print list_num #打印下頁碼     #調用新url鏈接    # for listnum in len(list_num):    page = BeautifulSoup(getPage(href))    em_list = page.find_all('em')  #匹配em內容    div_list = page.find_all('td',{'align':'center'})  #匹配 <td align=center>這樣的內容    #初始化n    n = 0    #將雙色球數字信息寫入num.txt文件    fp = open("num.txt" ,"w")    for div in em_list:      emnum1 = div.get_text()      # print emnum1      text = div.get_text()      text = text.encode('utf-8')      #print title      n=n+1      if n==7:        text = text + "/n"        n=0      else:        text = text + ","      fp.write(str(text))    fp.close()    #將日期信息寫入date.txt文件    fp = open("date.txt" ,"w")    for div in div_list:      text = div.get_text().strip('')      # print text      list_num = re.findall('/d{4}-/d{2}-/d{2}',text)      list_num = str(list_num[::1])      list_num = list_num[3:13]      if len(list_num) == 0:        continue      elif len(list_num) > 1:        fp.write(str(list_num)+'/n')    fp.close()    #將num.txt和date.txt文件進行整合寫入hun.txt文件中    #格式如下：    #('2016-05-03', '09,12,24,28,29,30,02')    #('2016-05-01', '06,08,13,14,22,27,10')    #('2016-04-28', '03,08,13,14,15,30,04')    #    fp01 = open("date.txt","r")    a=[]    for line01 in fp01:      a.append(line01.strip('/n'))      # print a    fp01.close()    fp02 = open("num.txt","r")    b=[]    for line02 in fp02:      b.append(line02.strip('/n'))      # print b    fp02.close()    fp = open("hun.txt" ,"a")    for cc in zip(a,b): #使用zip方法合并      print cc      fp.write(str(cc) + '/n')    fp.close()#===============================================================================if __name__=="__main__":  pageNum = getPageNum(url)  print pageNum  getpagetext = getText(url)  print getpagetext