# - * - coding: utf-8 - * - 



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

Def writecsv (item) : 
With the open (' ershou. CSV ', 'a', encoding="utf-8") as f: # CSV file name 
Writer.=the CSV writer (f) 
Try: 
Writer. Writerow (item) 
Except: 
Print (' write error! ') 


If __name__=="__main__ ': 
Headers={' the user-agent ':' Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/81.0.4044.92 Safari/537.3 '} 

Start_url='https://cd.ke.com/ershoufang/damian/pg' 
For x in range (1,76) : 
Url=start_url + STR (x) 
HTML=requests. Get (url, headers=headers) 
Time. Sleep (3) 
The selector=etree. HTML (HTML. Text) 


Xiaoqulist=selector. Xpath ('//* [@ id="beike"]/div [1]/div [4]/div [1]/div [4]/ul/li ') 
For xiaoqu in xiaoqulist: 

# building name 
Mingcheng=xiaoqu. Xpath (' div/div [2]/div [1]/div/a/text () ') [0] 

# building information 
Xinxi=xiaoqu. Xpath (' div/div [2]/div [2]/text () ') [1] 

# average 
Junjia=xiaoqu. Xpath (' div/div [2]/div [5]/div [2]/span/text () ') [0] 

# price 
Zongjia=xiaoqu. Xpath ('//div/div [5]/div/@/span/text () ') [0] 


Item=[mingcheng, xinxi, junjia, zongjia] 
Writecsv (item) 
Print (' londing: ', mingcheng) 

CodePudding user response:

 
The from multiprocessing import Pool 
Def main (num1) : 
Pass 
Print (" over a ") 
If __name__=="__main__ ': 
Pool=pool (8) # number is the number of process need to, as long as you are memory and CPU are strong enough, 
# pool. The map (the main, a list) is the main process, pay attention to do not add parentheses, the list is an iterative object, the inside of the element is the main parameters () need 
Pool. The start () # multi-process 
Pool. The join () # of all the main process for the child, to the end of the 
Print (" complete ") 

CodePudding user response: