本站爬图测试

赵乾舟

赵乾舟

1. import requests
   
2. import os
   
3. from lxml import etree
   
4. if not os.path.exists('c:/cl'):
   
5.     os.mkdir('c:/cl')
   
6. url = 'http://zhaoqianzhou.com/forum.php?mod=viewthread&tid=325&extra='
   
7. UA = {'user-agent':'Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/86.0.4240.198 Safari/537.36'}
   
8. respon = requests.get( url = url,headers=UA).text
   
9. jiexi = etree.HTML(respon)
   
10. picurl = jiexi.xpath('//div[@class="t_fsz"]//@file')
    
11. for i in picurl:
    
12.     newpicurl = 'http://zhaoqianzhou.com/'+i
    
13.     picdate = requests.get(url=newpicurl,headers=UA).content
    
14.     picname = newpicurl.split('/')[-1]
    
15.     pinadd = 'c:/cl/'+ picname
    
16.     with open(pinadd,'wb') as tu:
    
17.         tu.write(picdate)
    
18.         print(picname,'下载完成')

复制代码