python爬虫（6）——正则表达式（三）

 1 from urllib import request
 2 import re
 3 
 4 def HTMLspider(url,startPage,endPage):
 5     
 6     #作用：负责处理URL，分配每个URL去发送请求
 7     
 8     for page in range(startPage,endPage+1):
 9         filename="第" + str(page) + "页.html"
10     
11         #组合为完整的url
12         fullurl=url + str(page)
13 
14         #调用loadPage()发送请求，获取HTML页面
15         html=loadPage(fullurl,filename)
16 
17 
18 
19 def loadPage(fullurl,filename):
20     #获取页面
21     response=request.urlopen(fullurl)
22     Html=response.read().decode(‘utf-8‘)
23     #print(Html)
24    
25     #正则编译，获取房产信息
26     info_pattern=r‘data-el="region">(.+?)</div>‘
27     info_list=re.findall(info_pattern,Html)
28     #print(info_list)
29     #正则编译，获取房产价格
30     price_pattern=r‘<div class="totalPrice"><span>\d+</span>万‘
31     price_list=re.findall(price_pattern,Html)
32     #print(price_list)
33 
34     writePage(price_list,info_list,filename)
35 
36 
37 
38 
39 def writePage(price_list,info_list,filename):
40     """
41     将服务器的响应文件保存到本地磁盘
42     """
43     list1=[]
44     list2=[]
45     for i in price_list:
46         i=‘-------------->>>>>Price:‘ + i[30:-8] + ‘万‘
47         list1.append(i)
48         #print(i[30:-8])
49     for j in info_list:
50         j=j.replace(‘</a>‘,‘ ‘*10)
51         j=j[:10] + ‘ ‘*5 +  ‘---------->>>>>Deatil information:  ‘ + j[10:] + ‘ ‘*5
52         list2.append(j)
53     #print(j)
54 
55     for each in zip(list2,list1):
56         print(each)
57 
58 
59 
60     print("正在存储"+filename)
61     #with open(filename,‘wb‘) as f:
62      #   f.write(html)
63 
64 
65     print("--"*30)
66 
67 
68 if __name__=="__main__":
69     #输入需要下载的起始页和终止页，注意转换成int类型
70     startPage=int(input("请输入起始页："))
71     endPage=int(input("请输入终止页："))
72 
73     url="https://sh.lianjia.com/ershoufang/"
74 
75     HTMLspider(url,startPage,endPage)
76 
77     print("下载完成！")