python爬虫教程：《利用Python爬取表情包》

 1  
 2 ‘‘‘
 3 在学习过程中有什么不懂得可以加我的
 4 python学习交流扣扣qun，934109170
 5 群里有不错的学习教程、开发工具与电子书籍。
 6 与你分享python企业当下人才需求及怎么从零基础学习好python，和学习什么内容。
 7 ‘‘‘
 8 from pyquery import PyQuery as pq
 9 import requests
10 from redis import StrictRedis
11 o=0
12 headers={
13     ‘user-agent‘:‘Mozilla/5.0 (Windows NT 10.0; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/58.0.3029.110 Safari/537.36 SE 2.X MetaSr 1.0‘
14  
15 }
16  
17  
18 def xpan(canshu):
19     try:
20         url = ‘https://www.doutula.com/photo/list/?page=‘ + str(canshu)
21         sp = requests.get(url, headers=headers).text
22  
23         doc=pq(sp)
24         item=doc(‘.col-xs-6 img‘).items()
25  
26         for i in item:
27             cu=i.attr(‘data-original‘)
28  
29  
30  
31             #r(cu,‘F:/斗图的/%s.jpg‘%u)
32            # u+=1
33             #print(‘当前已保存%d张‘%u)
34             #print(cu)
35             redis = StrictRedis(host=‘172.18.200.5‘, port=6379, db=1, password=‘‘)
36             redis.sadd(‘斗图网下载图片的URL‘, cu)
37  
38     except Exception as e:
39  
40        print(‘出现错误‘,e.args)
41 a=int(input(‘请问你需要爬取多少页呢:‘))
42 print(‘正在爬取链接并保存到redis数据库中请稍等........‘)
43 for i in range(a):
44  
45    xpan(i+1)
46  
47 redis = StrictRedis(host=‘172.18.200.5‘, port=6379, db=1, password=‘‘)
48 redis.srem(‘斗图网下载图片的URL‘,‘None‘)
49 for i in redis.smembers(‘斗图网下载图片的URL‘):
50     t=str(i,encoding=‘utf8‘)
51     #print(t)
52     r=t.split(‘/‘)[-1]
53     dizhi=‘F:/斗图/‘+r
54     req=requests.get(t)
55     with open(dizhi,‘wb‘)as p:
56         p.write(req.content)
57         print(‘保存完毕 已保存了%d张‘%o)
58         o+=1