Python3 黑板客爬虫闯关第一关

  

   

    

     

    
    

     

      #coding=utf-8
     
    
   

    

     

    
    

     

      import re
     
    
   

    

     

    
    

     

      import requests
     
    
   

    

     

    
    

     

      from requests.exceptions import RequestException
     
    
   

    

     

    
    

     

      from bs4 import BeautifulSoup
     
    
   

    

     

    
    

     
 
     
    
   

    

     

    
    

     

      def getHtml(url):
     
    
   

    

     

    
    

     
 try:
     
    
   

    

     

    
    

     

       headers = {'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:56.0) Gecko/20100101 Firefox/56.0'}  
     
    
   

    

     

    
    

     

       response = requests.get(url,headers = headers)
     
    
   

    

     

    
    

     
 if response.status_code == 200:
     
    
   

    

     

    
    

     
 return response.text
     
    
   

    

     

    
    

     
 return None
     
    
   

    

     

    
    

     
 except RequestException:
     
    
   

    

     

    
    

     
 return None
     
    
   

    

     

    
    

     
 
     
    
   

    

     

    
    

     

      if __name__=='__main__':
     
    
   

    

     

    
    

     

       start_url = "http://www.heibanke.com/lesson/crawler_ex00/"
     
    
   

    

     

    
    

     

       real_url = start_url
     
    
   

    

     

    
    

     
 while 1:#while 1 的运行速度比while True 要快那么一点
     
    
   

    

     

    
    

     
 print ("当前请求页面:{}".format(real_url))
     
    
   

    

     

    
    

     

       html = getHtml(real_url)
     
    
   

    

     

    
    

     

       soup = BeautifulSoup(html,"lxml")
     
    
   

    

     

    
    

     

       source =soup.select_one('h3').text
     
    
   

    

     

    
    

     

       num = re.findall('\d+',source)
     
    
   

    

     

    
    

     
 if len(num) == 0:
     
    
   

    

     

    
    

     
 break
     
    
   

    

     

    
    

     

       real_url =  start_url + num[0]
     
    
  
 

考察点：url的拼接，BeautifulSoup库及正则表达式库的使用。

文章来源: blog.csdn.net，作者：悦来客栈的老板，版权归原作者所有，如需转载，请联系作者。

原文链接：blog.csdn.net/qq523176585/article/details/83019159