the from LXML import etree 
The import requests 
The import CSV 
The import time 


Def spiders () : 
# define the crawler head 
Headers={' the user-agent ':' Mozilla/5.0 (Windows NT 10.0; Win64; X64) '
'AppleWebKit/537.36 (KHTML, like Gecko) Chrome/80.0.3987.149 Safari/537.36'} 
# using a for loop structure in the first 10 pages URL, and GET request down 

Pre_url='https://shenzhen.qfang.com/sale/f' 
For x in range (2, 4) : 
HTML=requests. Get (pre_url + STR (x), headers=headers) 
Print (HTML. Status_code) 
# print (HTML content. Decode (' utf-8)) 
Time. Sleep (2) 

# initialization etree 
The selector=etree. HTML (HTML. Text) 

#/HTML/body/div [4]/div/div [1]/div [4]/ul/li 
# get housing list 
#/HTML/body/div [4]/div/div [1]/div [4]/ul/li 
House_list=selector. Xpath ("/HTML/body/div [4]/div/div [1]/div [4]/ul/li ") 
Print (house_list) 
For house in house_list: 
Apartment=house. Xpath (" div [2]/div [1]/a/text () ") [0] 
Print (apartment) 

#/HTML/body/div [4]/div/div [1]/div [4]/ul/li [1]/div [2]/div [2]/[1] p 
House_layout=house. Xpath (' div [2]/div p [1] [2]//text () ') [0] 

#/HTML/body/div [4]/div/div [1]/div [4]/ul/li [1]/div [2]/div [2]/[2] p 
Area=house. Xpath (' div [2]/div [2]/[2] p/text () ') [0] 

#/HTML/body/div [4]/div/div [1]/div [4]/ul/li [1]/div [2]/div [3] 
Region=house. Xpath (' div [2]/div [3]/a/text () ') [0] 

Total_price=house. Xpath (" div [3]/p/text () ") [0] 

The item=[apartment, house_layout, area, region, total_price] 
Data_writer (item) 
Print (' are fetching, apartment) 


Def data_writer (item) : 
With the open (' qfang_ershoufang. CSV ', 'a', encoding="utf-8", newline=' ') as csvfile: 
Writer.=the CSV writer (csvfile) 
Writer. Writerow (item) 

If __name__=="__main__ ': 
Spiders ()