python爬取gif动图【内涵福利】水平有限待完善

huole

1. import urllib.request
   
2. import re
   
3. import os,sys
   
4. import random
   
5. import time
   
6. 
   
7. 
   
8. def url_open(url):
   
9.     headers = {
   
10.         'Referer': 'http://bbbt.net/',
    
11.         'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/80.0.3987.162 Safari/537.36'
    
12.     }
    
13.     req = urllib.request.Request(url, headers=headers)
    
14.     response = urllib.request.urlopen(req)
    
15.     html = response.read().decode('utf-8')
    
16.     return html
    
17. 
    
18. def get_pages(each):
    
19.     html2 = url_open(each)
    
20.     t1 = re.search(r'<title>.{1,30}</title>',html2)
    
21.     title = t1.group()[7:-8]
    
22. 
    
23.     return title
    
24.     #print(title)
    
25. 
    
26. urllist = ['http://bbbt.net/tag/gif%E5%87%BA%E5%A4%84','http://bbbt.net/tag/%E7%A6%8F%E5%88%A9%E5%90%A7']
    
27. url = random.choice(urllist)
    
28. html = url_open(url)
    
29. urls = re.findall(r'http://bbbt.net/.{1,8}.html',html)
    
30. #print(set(urls))
    
31. 
    
32. for each in set(urls):
    
33.     title = get_pages(each)
    
34.     folder = str(title)
    
35. 
    
36.     os.chdir('D:/')
    
37.     os.mkdir(folder)
    
38.     os.chdir(folder)
    
39.     count = 1
    
40.     html1 = url_open(each)
    
41.     name = re.findall(r'<p>.{3,20}</p>', html1)
    
42.     print('相关信息：')
    
43.     for i in name:
    
44.         print(i[3:-4])
    
45.     #print(html1)
    
46.     img_addrs = re.findall(r'https://tva1.sinaimg.cn/.{1,7}/.{10,80}.gif',str(html1))
    
47.     #print(set(img_addrs))
    
48.     for each1 in set(img_addrs):
    
49. 
    
50.         headers = {
    
51.             'Referer': 'http://bbbt.net/',
    
52.             'User-Agent': 'Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/80.0.3987.162 Safari/537.36'
    
53.         }
    
54.         req = urllib.request.Request(each1, headers=headers)
    
55.         response = urllib.request.urlopen(req)
    
56.         mm_img = response.read()
    
57. 
    
58.         filename = str(count) + '.gif'
    
59.         print('下载第' + str(count) + '张图片')
    
60.         with open(filename, 'wb') as f:
    
61.             f.write(mm_img)
    
62.             count += 1
    
63. 
    
64. 
    
65. 
    

复制代码

Twilight6

我要去补补身体了