原创:Python爬虫实战之爬取美女照片

 1 #!/usr/bin/env python
 2 # -*- coding: utf-8 -*-
 3 import urllib.request
 4 import base64
 5 import time
 6 
 7 url_a = ‘http://jandan.net/ooxx/‘#网站前一部分
 8 need = ‘20200217-‘#后一部分
 9 need_a = 147#后一部分的后一部分
10 
11 
12 def base(word):#base64编码
13     outcome = base64.b64encode(word.encode("utf-8"))#编码后
14     url = url_a + outcome.decode(‘utf-8‘) + ‘#comments‘
15     web(url)
16 
17 def web(url):
18     response = urllib.request.urlopen(url)
19     html = response.read().decode(‘utf-8‘)
20     a = html.find(‘<img src="//‘)#从这个下标开始
21     i = 0#用来区别文件名
22     while a != -1:
23         b = html.find(‘.jpg‘,a,a+250)#到这个下标为止
24         if b != -1:
25             c = ‘http://‘ + html[a+12:b+4]#图片网址    
26             name = ‘picture\\‘ + str(i) + str(need_a) + ‘.jpg‘#文件名
27             get_jpg(c,name)
28         else:
29             b = a + 12
30         a = html.find(‘<img src="//‘,b)#循环查找
31         i += 1
32 
33 def get_jpg(address,filename):
34     get = urllib.request.urlopen(address)#打开新网址
35     jpg = get.read()
36     with open(filename,‘wb‘) as f:#写入图片
37         f.write(jpg)
38     print("Succeed!")
39 
40 while need_a >=100:#逐减
41     addition = need + str(need_a)
42     base(addition)
43     need_a -= 1
44     time.sleep(10)#停顿防止被反爬