600M左右的ooxx图片爬取

mongoole

1.参考博客：解密ooxx妹子图的url
2.学习一下，顺便自己来操作一波。
3.图片下载保存的地址，请同学们根据自己的需要更改！

1. #coding:utf-8
   
2. 
   
3. import requests
   
4. import urllib.request
   
5. from lxml import etree
   
6. import _md5
   
7. import hashlib
   
8. import base64
   
9. import time
   
10. 
    
11. 
    
12. def get_response(url,headers):
    
13. 
    
14.     response = requests.get(url,headers=headers)
    
15.     html = response.text
    
16.     # print(html)
    
17.     get_hash(html)
    
18. 
    
19. def get_hash(html):
    
20. 
    
21.     selector = etree.HTML(html)
    
22.     hashs = selector.xpath('//li/div/div/div[2]/p/span/text()')        #获取到图片的hash值
    
23.     # print(hashs)
    
24.     get_url(hashs)
    
25. 
    
26. # def get_js():
    
27. #     global r
    
28. #     js = 'http://cdn.jandan.net/static/min/91798e4c623fa60181a31d543488217e7f2ZE0GM.30100001.js'
    
29. #     r = 'zvvhmFaGE7I8FjdHv8XaZ5O6dmOltKa3'
    
30. 
    
31. def _md5(value):
    
32.     ''''md5加密'''
    
33.     m = hashlib.md5()
    
34.     m.update(value.encode('utf-8'))
    
35.     return m.hexdigest()
    
36. 
    
37. 
    
38. def _base64_decode(data):
    
39.     '''bash64解码'''
    
40.     missing_padding = 4 - len(data) % 4
    
41.     if missing_padding:
    
42.         data += '=' * missing_padding
    
43.     return base64.b64decode(data)
    
44. 
    
45. 
    
46. def get_url(hashs):
    
47.     for i in hashs:
    
48.         # print(i)
    
49.         get_imgurl(i,r)
    
50.         # time.sleep(2)
    
51. 
    
52. 
    
53. def get_imgurl(m,r='',d=0):
    
54. 
    
55.     '''解密获取图片链接'''
    
56.     e = "DECODE"
    
57.     q = 4
    
58.     r = _md5(r)
    
59.     o = _md5(r[0:0 + 16])
    
60.     n = _md5(r[16:16 + 16])
    
61.     l = m[0:q]
    
62.     c = o + _md5(o + l)
    
63.     m = m[q:]
    
64.     k = _base64_decode(m)
    
65.     url = k.decode('utf-8', errors='ignore')
    
66.     url = 'http://w' + url
    
67. 
    
68.     # print(url)
    
69. 
    
70.     download_img(url)
    
71. 
    
72. def download_img(url):
    
73.     # print(url)
    
74.     filename = url.split('/')[-1]
    
75.     opener = urllib.request.build_opener()
    
76. 
    
77.     try:
    
78.         opener.open(url)
    
79.         urllib.request.urlretrieve(url,'E:\\study\\spider\\煎蛋网\\jandanimg\\' + filename)
    
80. 
    
81.     except urllib.error.HTTPError:
    
82.         print(url + '访问页面出错')
    
83.         # time.sleep(1)
    
84. 
    
85.     except urllib.error.URLError:
    
86.         print(url + '访问页面出错')
    
87.         # time.sleep(1)
    
88. 
    
89. 
    
90. 
    
91. 
    
92. if __name__ == '__main__':
    
93.     url_tg = 'http://jandan.net/ooxx'
    
94.     headers = {'user-agent':'Mozilla/5.0 (Windows NT 6.1; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/67.0.3396.99 Safari/537.36'}
    
95. 
    
96.     #r这个参数我看了下是固定值
    
97.     r = 'zvvhmFaGE7I8FjdHv8XaZ5O6dmOltKa3'
    
98.     for i in range(1,43):
    
99.         url = url_tg + '/page-%s#comments'%i
    
100.         print('%s--------开始下载'%url)
     
101.         get_response(url,headers)
     
102.         print('%s--------下载完成'%url)
     
103.         time.sleep(10)
     

复制代码

titanss

亲测可用，棒棒哒
不知道煎蛋网会不会很生气

mongoole

titanss 发表于 2018-7-22 23:19
亲测可用，棒棒哒
不知道煎蛋网会不会很生气

不会吧，他们那么可爱！