爬取网贷之家的数据

代码还是借鉴数据之魂大大的，有兴趣的可以去看看他的博客,不多说直接上代码：

 1 #!/usr/bin/env python3
 2 # -*- coding: utf-8 -*-
 3 import urllib
 4 import urllib.request
 5 import re
 6 import random
 7 #抓取所需内容
 8 user_agent = ["Mozilla/5.0 (Windows NT 10.0; WOW64)", ‘Mozilla/5.0 (Windows NT 6.3; WOW64)‘,
 9               ‘Mozilla/5.0 (Windows NT 6.1) AppleWebKit/537.11 (KHTML, like Gecko) Chrome/23.0.1271.64 Safari/537.11‘,
10               ‘Mozilla/5.0 (Windows NT 6.3; WOW64; Trident/7.0; rv:11.0) like Gecko‘,
11               ‘Mozilla/5.0 (Windows NT 5.1) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/28.0.1500.95 Safari/537.36‘,
12               ‘Mozilla/5.0 (Windows NT 6.1; WOW64; Trident/7.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; .NET4.0C; rv:11.0) like Gecko)‘,
13               ‘Mozilla/5.0 (Windows; U; Windows NT 5.2) Gecko/2008070208 Firefox/3.0.1‘,
14               ‘Mozilla/5.0 (Windows; U; Windows NT 5.1) Gecko/20070309 Firefox/2.0.0.3‘,
15               ‘Mozilla/5.0 (Windows; U; Windows NT 5.1) Gecko/20070803 Firefox/1.5.0.12‘,
16               ‘Opera/9.27 (Windows NT 5.2; U; zh-cn)‘,
17               ‘Mozilla/5.0 (Macintosh; PPC Mac OS X; U; en) Opera 8.0‘,
18               ‘Opera/8.0 (Macintosh; PPC Mac OS X; U; en)‘,
19               ‘Mozilla/5.0 (Windows; U; Windows NT 5.1; en-US; rv:1.8.1.12) Gecko/20080219 Firefox/2.0.0.12 Navigator/9.0.0.6‘,
20               ‘Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 6.1; Win64; x64; Trident/4.0)‘,
21               ‘Mozilla/4.0 (compatible; MSIE 8.0; Windows NT 6.1; Trident/4.0)‘,
22               ‘Mozilla/5.0 (compatible; MSIE 10.0; Windows NT 6.1; WOW64; Trident/6.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; InfoPath.2; .NET4.0C; .NET4.0E)‘,
23               ‘Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.1 (KHTML, like Gecko) Maxthon/4.0.6.2000 Chrome/26.0.1410.43 Safari/537.1 ‘,
24               ‘Mozilla/5.0 (compatible; MSIE 10.0; Windows NT 6.1; WOW64; Trident/6.0; SLCC2; .NET CLR 2.0.50727; .NET CLR 3.5.30729; .NET CLR 3.0.30729; Media Center PC 6.0; InfoPath.2; .NET4.0C; .NET4.0E; QQBrowser/7.3.9825.400)‘,
25               ‘Mozilla/5.0 (Windows NT 6.1; WOW64; rv:21.0) Gecko/20100101 Firefox/21.0 ‘,
26               ‘Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.1 (KHTML, like Gecko) Chrome/21.0.1180.92 Safari/537.1 LBBROWSER‘,
27               ‘Mozilla/5.0 (compatible; MSIE 10.0; Windows NT 6.1; WOW64; Trident/6.0; BIDUBrowser 2.x)‘,
28               ‘Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/536.11 (KHTML, like Gecko) Chrome/20.0.1132.11 TaoBrowser/3.0 Safari/536.11‘]
29 url=‘http://shuju.wdzj.com‘
30 request=urllib.request.Request(url=url,headers={"User-Agent":random.choice(user_agent)})#随机从user_agent列表中抽取一个元素
31 response=urllib.request.urlopen(request)
32 content=response.read().decode(‘utf8‘)      #读取网页内容
33 pattern=re.compile(r‘\/\w{4}\-\w{4}\-\d*\.\w{4}\S{2}[\u4e00-\u9fa5]{2,6}|\/\w{4}\-\w{4}\-\d*\.\w{4}\S{2}\S{2,7}|<div>\d*.\d*</div>‘)
34 match = re.findall(pattern,content)
35 a=[]                                          #第一步数据处理存放地址
36 b=[]                                          #第二步数据处理存放地址
37 for i in match:
38     try:
39         (n,m)=i.split(">")
40         a.append(m)
41     except:
42         (n, m,g) = i.split(">", 3)
43         a.append(m)                        #数据处理第一步
44 for q in a:
45     try:
46         (q1,q2)=q.split("<")
47         b.append(q1)
48     except:
49         b.append(q)                        #数据处理第二步
50 print(‘平台‘,‘\t‘,‘成交量‘,‘   ‘,‘\t‘,‘平均收益率‘,‘\t‘,‘平均借款期限‘,‘\t‘,‘待还余额‘)
51 for v in range(0,len(b),5):  #原网页有5列数据，所以步长为5
52     print(b[v],‘\t‘,b[v+1],‘ ‘,‘\t‘,b[v+2],‘  ‘,‘\t‘,b[v+3],‘  ‘,‘\t‘,b[v+4])

正则表达式不是太熟，写的有点烂，不过基本能得出结果，下面附上部分爬取结果：