Python3 css选择器实战(二)：爬取猫眼电影网

  

   

    

     

    
    

     

      #coding=utf-8
     
    
   

    

     

    
    

     

      import re
     
    
   

    

     

    
    

     

      import time
     
    
   

    

     

    
    

     

      import requests
     
    
   

    

     

    
    

     

      from requests.exceptions import RequestException
     
    
   

    

     

    
    

     

      from bs4 import BeautifulSoup
     
    
   

    

     

    
    

     

      from prettytable import PrettyTable
     
    
   

    

     

    
    

     
 
     
    
   

    

     

    
    

     
 
     
    
   

    

     

    
    

     

      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__':
     
    
   

    

     

    
    

     

       lmovie = []
     
    
   

    

     

    
    

     

       lactor = []
     
    
   

    

     

    
    

     

       ltime = []
     
    
   

    

     

    
    

     

       lscore = []
     
    
   

    

     

    
    

     

       table = PrettyTable(['NO.','电影','主演','上映时间','猫眼评分'])
     
    
   

    

     

    
    

     

       index = 0
     
    
   

    

     

    
    

     
 for page in range(0,100,10):
     
    
   

    

     

    
    

     

       url = 'http://maoyan.com/board/4?offset={}'.format(page)
     
    
   

    

     

    
    

     

       Html = getHtml(url)
     
    
   

    

     

    
    

     
 if Html is None:
     
    
   

    

     

    
    

     

       contine
     
    
   

    

     

    
    

     

       Soup = BeautifulSoup(Html,'lxml')
     
    
   

    

     

    
    

     

       names = Soup.select('div.movie-item-info > p:nth-of-type(1)')
     
    
   

    

     

    
    

     
 for name in names:
     
    
   

    

     

    
    

     

       lmovie.append(name.text)
     
    
   

    

     

    
    

     

       actors = Soup.select('div.movie-item-info > p:nth-of-type(2)')
     
    
   

    

     

    
    

     
 for actor in actors:
     
    
   

    

     

    
    

     

       actor = actor.text
     
    
   

    

     

    
    

     

       actor = actor.split('：')[-1]
     
    
   

    

     

    
    

     

       lactor.append(actor.strip())
     
    
   

    

     

    
    

     

       releasetimes = Soup.select('div.movie-item-info > p:nth-of-type(3)')
     
    
   

    

     

    
    

     
 for retime in releasetimes:
     
    
   

    

     

    
    

     

       retime = retime.text
     
    
   

    

     

    
    

     

       retime = retime.split('：')[-1]
     
    
   

    

     

    
    

     

       ltime.append(retime)
     
    
   

    

     

    
    

     

       scores = Soup.select('p.score > i:nth-of-type(1)')
     
    
   

    

     

    
    

     
 for score in scores:
     
    
   

    

     

    
    

     

       lscore.append(score.text)
     
    
   

    

     

    
    

     

       frascores = Soup.select('p.score > i:nth-of-type(2)')
     
    
   

    

     

    
    

     
 for i in range(len(frascores)):
     
    
   

    

     

    
    

     

       lscore[index] += frascores[i].text
     
    
   

    

     

    
    

     

       index += 1
     
    
   

    

     

    
    

     
 
     
    
   

    

     

    
    

     

       time.sleep(1)
     
    
   

    

     

    
    

     
 for i in range(100):
     
    
   

    

     

    
    

     

       table.add_row([str(i+1),lmovie[i],lactor[i],ltime[i],lscore[i]])
     
    
   

    

     

    
    

     
 print (table)
     
    
   

    

     

    
    

     
 
     
    
   

    

     

    
    

     
 
     
    
   

    

     

    
    

     
 
     
    
   

    

     

    
    

     
 
     
    
   

    

     

    
    

     
 
     
    
   

    

     

    
    

     
 
     
    
   

    

     

    
    

     
 
     
    
   

    

     

    
    

     
 
     
    
   

    

     

    
    

     
 
     
    
   

    

     

    
    

     
 
     
    
   

    

     

    
    

     
 
     
    
   

    

     

    
    

     
 
     
    
   

    

     

    
    

     
 
     
    
   

    

     

    
    

     
 
     
    
   

    

     

    
    

     
 
     
    
  
 

总结：用nth-of-type的感觉太爽了，代码也要优美很多。

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/82917075