python 爬取网页

pip install Beautifulsoup4

  

   

    

     

    
    

     
 
     
    
   

    

     

    
    

     

      from bs4 import BeautifulSoup
     
    
   

    

     

    
    

     

      import requests
     
    
   

    

     

    
    

     

      if __name__=='__main__':
     
    
   

    

     

    
    

     

       target='http://www.luoxia.com/daqindiguo/84575.htm'
     
    
   

    

     

    
    

     
 #kv = {'user-agent': 'Mozilla/5.0'}
     
    
   

    

     

    
    

     
 try:
     
    
   

    

     

    
    

     

       req=requests.get(url=target)
     
    
   

    

     

    
    

     

       html=req.text
     
    
   

    

     

    
    

     

       bf=BeautifulSoup(html,"lxml")
     
    
   

    

     

    
    

     

       texts=bf.find_all('div',id="nr1")
     
    
   

    

     

    
    

     
 
     
    
   

    

     

    
    

     

       aaa=texts[0].text.replace('\xa0','')
     
    
   

    

     

    
    

     

       bbb=aaa.replace("\n\n","")
     
    
   

    

     

    
    

     

       print(bbb)
     
    
   

    

     

    
    

     
 except Exception as e:
     
    
   

    

     

    
    

     

       print("爬取异常",e)
     
    
  
 

文章来源: blog.csdn.net，作者：网奇，版权归原作者所有，如需转载，请联系作者。

原文链接：blog.csdn.net/jacke121/article/details/89462976