爬取彼岸网站壁纸

赵乾舟

1. import requests
   
2. from lxml import etree
   
3. import time
   
4. start_time = time.time()
   
5. 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'}
   
6. for ye in range(1,10):      #定义网址和爬取页数
   
7.     if ye == 1 :
   
8.         url = 'http://www.netbian.com/meinv'
   
9.     else:
   
10.         url = f'http://www.netbian.com/meinv/index_{ye}.htm'
    
11.     #print(url)
    
12.     respon = requests.get(url=url,headers=UA).text
    
13.     jiexi = etree.HTML(respon)
    
14.     picurl = jiexi.xpath('//*[@id="main"]/div[3]/ul/li/a/@href')
    
15.     picurl = ['http://www.netbian.com'+picurl for picurl in picurl]
    
16.     #print(picurl)
    
17.     for i in picurl:
    
18.         #print(i)
    
19.         respon = requests.get(url=i, headers=UA).text
    
20.         jiexi = etree.HTML(respon)
    
21.         lasturl = jiexi.xpath('//*[@id="main"]/div[3]/div/p/a/img/@src')
    
22.         for j in lasturl:
    
23.             respon =requests.get(url=j).content
    
24.             picname = j.split('/')[-1]
    
25.             pinadd = 'c:/cl/a/'+picname
    
26.             with open(pinadd,'wb') as a:
    
27.                 a.write(respon)
    
28.                 print(picname,'下载完成。')
    
29. end_time = time.time()
    
30. shijian = end_time - start_time
    
31. print(f'一共用时{shijian}秒')

复制代码