本文实例讲述了Python数据分析之获取双色球历史信息的方法。分享给大家供大家参考，具体如下：
每个人都有一颗中双色球大奖的心，对于技术人员来说，通过技术分析，可以增加中奖几率，现使用python语言收集历史双色球中奖信息，之后进行预测分析。
说明：采用2016年5月15日获取的双色球数据为基础进行分析，总抽奖数1940次。
初级代码，有些内容比较繁琐，有更好的代码，大家可以分享。
|
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
|
#!/usr/bin/python# -*- coding:UTF-8 -*-#coding:utf-8#author:levycui#date:20160513#Description:双色球信息收集import urllib2from bs4 import BeautifulSoup #采用BeautifulSoupimport osimport re#伪装成浏览器登陆,获取网页源代码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 双色球首页url = 'http://kaijiang.zhcw.com/zhcw/html/ssq/list_1.html'#===============================================================================#获取url总页数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#===============================================================================#获取每页双色球的信息def getText(url): for list_num in range(1,getPageNum(url)): #从第一页到第getPageNum(url)页 print list_num #打印下页码 href = 'http://kaijiang.zhcw.com/zhcw/html/ssq/list_'+str(list_num)+'.html' #调用新url链接 # for listnum in len(list_num): page = BeautifulSoup(getPage(href)) em_list = page.find_all('em') #匹配em内容 div_list = page.find_all('td',{'align':'center'}) #匹配 <td align=center>这样的内容 #初始化n n = 0 #将双色球数字信息写入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() #将日期信息写入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() #将num.txt和date.txt文件进行整合写入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 |
数据样例：
|
1
2
3
|
('2015-03-03', '09,11,16,18,23,24,10')('2015-03-01', '08,09,10,13,29,30,01')('2015-02-26', '04,07,10,16,23,25,10') |
希望本文所述对大家Python程序设计有所帮助。
原文链接：http://blog.csdn.net/levy_cui/article/details/51394450
